[RELEASE-ONLY Change] Push ROCm images on RC (#137148)

* [RELEASE-ONLY Change] Push ROCm images on RC

We usually don't need to push docker images on RC, but for 2.5.0 release a cherry pick for ROCm actually modified docker images.

Do this for ROCm only to be safe.
After the release, think about what's the desired behavior and implement this in a more generic way.

* Hardcode 2.5 in the tag

.ci/docker/aotriton_version.txt

@@ -1,5 +1,5 @@
-0.6b
+0.7b
 manylinux_2_17
 rocm6.2
-7f07e8a1cb1f99627eb6d77f5c0e9295c775f3c7
-e4ab195d2bd19e939c675a13280c29714c6ef9f2cf420690da150fa0cac043b1
+9be04068c3c0857a4cfd17d7e39e71d0423ebac2
+3e9e1959d23b93d78a08fcc5f868125dc3854dece32fd9458be9ef4467982291

.ci/docker/build.sh

@@ -286,18 +286,7 @@ case "$image" in
     TRITON=yes
     ;;
   pytorch-linux-focal-rocm-n-1-py3)
-    ANACONDA_PYTHON_VERSION=3.8
-    GCC_VERSION=9
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    ROCM_VERSION=6.0
-    NINJA_VERSION=1.9.0
-    CONDA_CMAKE=yes
-    TRITON=yes
-    ;;
-  pytorch-linux-focal-rocm-n-py3)
-    ANACONDA_PYTHON_VERSION=3.8
+    ANACONDA_PYTHON_VERSION=3.10
     GCC_VERSION=9
     PROTOBUF=yes
     DB=yes
@@ -307,6 +296,17 @@ case "$image" in
     CONDA_CMAKE=yes
     TRITON=yes
     ;;
+  pytorch-linux-focal-rocm-n-py3)
+    ANACONDA_PYTHON_VERSION=3.10
+    GCC_VERSION=9
+    PROTOBUF=yes
+    DB=yes
+    VISION=yes
+    ROCM_VERSION=6.2
+    NINJA_VERSION=1.9.0
+    CONDA_CMAKE=yes
+    TRITON=yes
+    ;;
   pytorch-linux-jammy-xpu-2024.0-py3)
     ANACONDA_PYTHON_VERSION=3.9
     GCC_VERSION=11

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

@@ -1 +1 @@
-cc981feba10a3f4c2e46f3fe368e8fcf5f5643df
+91b14bf5593cf58a8541f3e6b9125600a867d4ef

.ci/docker/ci_commit_pins/triton.txt

@@ -1 +1 @@
-757b6a61e7df814ba806f498f8bb3160f84b120c
+5fe38ffd73c2ac6ed6323b554205186696631c6f

.ci/docker/common/install_aotriton.sh

@@ -4,12 +4,12 @@ set -ex
 
 source "$(dirname "${BASH_SOURCE[0]}")/common_utils.sh"
 
-TARBALL='aotriton.tar.bz2'
+TARBALL='aotriton.tar.gz'
 # This read command alwasy returns with exit code 1
 read -d "\n" VER MANYLINUX ROCMBASE PINNED_COMMIT SHA256 < aotriton_version.txt || true
 ARCH=$(uname -m)
 AOTRITON_INSTALL_PREFIX="$1"
-AOTRITON_URL="https://github.com/ROCm/aotriton/releases/download/${VER}/aotriton-${VER}-${MANYLINUX}_${ARCH}-${ROCMBASE}-shared.tar.bz2"
+AOTRITON_URL="https://github.com/ROCm/aotriton/releases/download/${VER}/aotriton-${VER}-${MANYLINUX}_${ARCH}-${ROCMBASE}-shared.tar.gz"
 
 cd "${AOTRITON_INSTALL_PREFIX}"
 # Must use -L to follow redirects

.ci/docker/common/install_miopen.sh

@@ -10,6 +10,21 @@ if [[ -z $ROCM_VERSION ]]; then
     exit 1;
 fi
 
+IS_UBUNTU=0
+ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"')
+case "$ID" in
+  ubuntu)
+    IS_UBUNTU=1
+    ;;
+  centos)
+    IS_UBUNTU=0
+    ;;
+  *)
+    echo "Unable to determine OS..."
+    exit 1
+    ;;
+esac
+
 # To make version comparison easier, create an integer representation.
 save_IFS="$IFS"
 IFS=. ROCM_VERSION_ARRAY=(${ROCM_VERSION})
@@ -58,8 +73,7 @@ MIOPEN_CMAKE_COMMON_FLAGS="
 "
 # Pull MIOpen repo and set DMIOPEN_EMBED_DB based on ROCm version
 if [[ $ROCM_INT -ge 60200 ]] && [[ $ROCM_INT -lt 60300 ]]; then
-    echo "ROCm 6.2 MIOpen does not need any patches, do not build from source"
-    exit 0
+    MIOPEN_BRANCH="release/rocm-rel-6.2-staging"
 elif [[ $ROCM_INT -ge 60100 ]] && [[ $ROCM_INT -lt 60200 ]]; then
     echo "ROCm 6.1 MIOpen does not need any patches, do not build from source"
     exit 0
@@ -93,12 +107,21 @@ else
     exit 1
 fi
 
-yum remove -y miopen-hip
+
+if [[ ${IS_UBUNTU} == 1 ]]; then
+  apt-get remove -y miopen-hip
+else
+  yum remove -y miopen-hip
+fi
 
 git clone https://github.com/ROCm/MIOpen -b ${MIOPEN_BRANCH}
 pushd MIOpen
 # remove .git to save disk space since CI runner was running out
 rm -rf .git
+# Don't build CK to save docker build time
+if [[ $ROCM_INT -ge 60200 ]]; then
+    sed -i '/composable_kernel/d' requirements.txt
+fi
 # Don't build MLIR to save docker build time
 # since we are disabling MLIR backend for MIOpen anyway
 if [[ $ROCM_INT -ge 50400 ]] && [[ $ROCM_INT -lt 50500 ]]; then
@@ -111,10 +134,15 @@ cmake -P install_deps.cmake --minimum
 
 # clean up since CI runner was running out of disk space
 rm -rf /tmp/*
-yum clean all
-rm -rf /var/cache/yum
-rm -rf /var/lib/yum/yumdb
-rm -rf /var/lib/yum/history
+if [[ ${IS_UBUNTU} == 1 ]]; then
+  apt-get autoclean && apt-get clean
+  rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+else
+  yum clean all
+  rm -rf /var/cache/yum
+  rm -rf /var/lib/yum/yumdb
+  rm -rf /var/lib/yum/history
+fi
 
 ## Build MIOpen
 mkdir -p build
@@ -131,7 +159,11 @@ make -j $(nproc) package
 # clean up since CI runner was running out of disk space
 rm -rf /usr/local/cget
 
-yum install -y miopen-*.rpm
+if [[ ${IS_UBUNTU} == 1 ]]; then
+  sudo dpkg -i miopen-hip*.deb
+else
+  yum install -y miopen-*.rpm
+fi
 
 popd
 rm -rf MIOpen

.ci/docker/manywheel/build.sh

@@ -135,7 +135,7 @@ fi
 )
 
 GITHUB_REF=${GITHUB_REF:-$(git symbolic-ref -q HEAD || git describe --tags --exact-match)}
-GIT_BRANCH_NAME=${GITHUB_REF##*/}
+GIT_BRANCH_NAME="2.5"
 GIT_COMMIT_SHA=${GITHUB_SHA:-$(git rev-parse HEAD)}
 DOCKER_IMAGE_BRANCH_TAG=${DOCKER_IMAGE}-${GIT_BRANCH_NAME}
 DOCKER_IMAGE_SHA_TAG=${DOCKER_IMAGE}-${GIT_COMMIT_SHA}

.ci/docker/triton_version.txt

@@ -1 +1 @@
-3.0.0
+3.1.0

.ci/docker/ubuntu-rocm/Dockerfile

@@ -68,6 +68,8 @@ RUN rm install_rocm.sh
 COPY ./common/install_rocm_magma.sh install_rocm_magma.sh
 RUN bash ./install_rocm_magma.sh
 RUN rm install_rocm_magma.sh
+ADD ./common/install_miopen.sh install_miopen.sh
+RUN bash ./install_miopen.sh ${ROCM_VERSION} && rm install_miopen.sh
 ENV ROCM_PATH /opt/rocm
 ENV PATH /opt/rocm/bin:$PATH
 ENV PATH /opt/rocm/hcc/bin:$PATH
@@ -121,5 +123,8 @@ RUN bash ./install_cache.sh && rm install_cache.sh
 ARG BUILD_ENVIRONMENT
 ENV BUILD_ENVIRONMENT ${BUILD_ENVIRONMENT}
 
+# Install LLVM dev version (Defined in the pytorch/builder github repository)
+COPY --from=pytorch/llvm:9.0.1 /opt/llvm /opt/llvm
+
 USER jenkins
 CMD ["bash"]

.ci/pytorch/build.sh

@@ -49,13 +49,8 @@ if [[ ${BUILD_ENVIRONMENT} == *"parallelnative"* ]]; then
 fi
 
 # Enable LLVM dependency for TensorExpr testing
-if [[ "$BUILD_ENVIRONMENT" == *rocm* ]]; then
-  export USE_LLVM=/opt/rocm/llvm
-  export LLVM_DIR=/opt/rocm/llvm/lib/cmake/llvm
-else
-  export USE_LLVM=/opt/llvm
-  export LLVM_DIR=/opt/llvm/lib/cmake/llvm
-fi
+export USE_LLVM=/opt/llvm
+export LLVM_DIR=/opt/llvm/lib/cmake/llvm
 
 if [[ "$BUILD_ENVIRONMENT" == *executorch* ]]; then
   # To build test_edge_op_registration

.ci/pytorch/common_utils.sh

@@ -198,7 +198,7 @@ function install_torchrec_and_fbgemm() {
 
 function clone_pytorch_xla() {
   if [[ ! -d ./xla ]]; then
-    git clone --recursive --quiet https://github.com/pytorch/xla.git
+    git clone --recursive -b r2.5 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)"

.circleci/scripts/binary_populate_env.sh

@@ -78,7 +78,7 @@ TRITON_VERSION=$(cat $PYTORCH_ROOT/.ci/docker/triton_version.txt)
 TRITON_CONSTRAINT="platform_system == 'Linux' and platform_machine == 'x86_64' and python_version < '3.13'"
 if [[ "$PACKAGE_TYPE" =~ .*wheel.* &&  -n "${PYTORCH_EXTRA_INSTALL_REQUIREMENTS:-}" ]]; then
   # Only linux Python < 3.13 are supported wheels for triton
-  TRITON_REQUIREMENT="triton==${TRITON_VERSION}; ${TRITON_CONSTRAINT}"
+  TRITON_REQUIREMENT="pytorch-triton==${TRITON_VERSION}; ${TRITON_CONSTRAINT}"
   if [[ -n "$PYTORCH_BUILD_VERSION" && "$PYTORCH_BUILD_VERSION" =~ .*dev.* ]]; then
       TRITON_SHORTHASH=$(cut -c1-10 $PYTORCH_ROOT/.ci/docker/ci_commit_pins/triton.txt)
       TRITON_REQUIREMENT="pytorch-triton==${TRITON_VERSION}+${TRITON_SHORTHASH}; ${TRITON_CONSTRAINT}"

.github/ci_commit_pins/xla.txt

@@ -1 +1 @@
-2eb4a60ed14a38260b85b0c765161f0ce45be6d1
+r2.5

.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"
+DISABLED_JOBS_URL = "https://ossci-metrics.s3.amazonaws.com/disabled-jobs.json?versionId=sxzMTP57qj.Vwz8dN1glkTK560Txq9W3"
 # and unstable jobs
-UNSTABLE_JOBS_URL = "https://ossci-metrics.s3.amazonaws.com/unstable-jobs.json"
+UNSTABLE_JOBS_URL = "https://ossci-metrics.s3.amazonaws.com/unstable-jobs.json?versionId=8f1.4S3MupuHXH8t0waxyGnPsGHJYdv9"
 
 # Some constants used to handle disabled and unstable jobs
 JOB_NAME_SEP = "/"

.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 = "main" -%}
+{%- set builder_branch = "release/2.5" -%}
 
 {%- 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@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}

.github/templates/linux_binary_build_workflow.yml.j2

@@ -142,10 +142,10 @@ jobs:
         with:
           name: !{{ config["build_name"] }}
           path: "${{ runner.temp }}/artifacts/"
-      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
-      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch, checkout_pr_head=False) }}
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: !{{ config["container_image"] }}
       - name: Test Pytorch binary
@@ -164,13 +164,13 @@ jobs:
         with:
           name: !{{ config["build_name"] }}
           path: "${{ runner.temp }}/artifacts/"
-      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
-      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch, checkout_pr_head=False) }}
       - 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@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: !{{ config["container_image"] }}
       - name: Test Pytorch binary

.github/templates/macos_binary_build_workflow.yml.j2

@@ -78,8 +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") }}
-      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch, checkout_pr_head=False) }}
       - 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

@@ -79,8 +79,8 @@ jobs:
     steps:
       !{{ common.setup_ec2_windows() }}
       !{{ set_runner_specific_vars() }}
-      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
-      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch, checkout_pr_head=False) }}
       - name: Populate binary env
         shell: bash
         run: |
@@ -121,8 +121,8 @@ jobs:
         with:
           name: !{{ config["build_name"] }}
           path: "${{ env.PYTORCH_FINAL_PACKAGE_DIR }}"
-      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
-      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch, checkout_pr_head=False) }}
       - name: Populate binary env
         shell: bash
         run: |

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

@@ -37,7 +37,7 @@ jobs:
       keep-going: ${{ steps.filter.outputs.keep-going }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: false
@@ -59,25 +59,25 @@ jobs:
     runs-on: ${{ matrix.runner }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - 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@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ inputs.docker-image-name }}
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
@@ -141,5 +141,5 @@ jobs:
         if: always()
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()

.github/workflows/_android-full-build-test.yml

@@ -37,7 +37,7 @@ jobs:
       keep-going: ${{ steps.filter.outputs.keep-going }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: false
@@ -59,25 +59,25 @@ jobs:
     runs-on: ${{ matrix.runner }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - 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@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ inputs.docker-image-name }}
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
@@ -186,5 +186,5 @@ jobs:
         if: always()
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()

.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@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         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@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - 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@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ inputs.docker-image-name }}
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
@@ -97,7 +97,7 @@ jobs:
         run: echo "IN_ARC_RUNNER=$([ -f /.inarc ] && echo true || echo false)" >> "$GITHUB_OUTPUT"
 
       - name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
-        uses: pytorch/test-infra/.github/actions/setup-nvidia@main
+        uses: pytorch/test-infra/.github/actions/setup-nvidia@release/2.5
         if: ${{ inputs.cuda-version != 'cpu' && steps.check_arc_runner.outputs.IN_ARC_RUNNER == 'false' }}
 
       - name: Output disk space left
@@ -206,5 +206,5 @@ jobs:
           file-suffix: bazel-${{ github.job }}_${{ steps.get-job-id.outputs.job-id }}
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         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@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.github-token }}
 
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           no-sudo: ${{ inputs.build_environment == 'linux-aarch64-binary-manywheel' || inputs.build_environment == 'linux-s390x-binary-manywheel' }}
 
@@ -195,7 +195,6 @@ 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
@@ -209,7 +208,7 @@ jobs:
       - name: Checkout pytorch/builder to builder dir
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -235,7 +234,7 @@ 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@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ inputs.DOCKER_IMAGE }}
 
@@ -293,7 +292,7 @@ jobs:
 
       - name: Teardown Linux
         if: always() && inputs.build_environment != 'linux-s390x-binary-manywheel'
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
 
       - 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@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.github-token }}
 
         # Setup the environment
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           no-sudo: ${{ inputs.build_environment == 'linux-aarch64-binary-manywheel' || inputs.build_environment == 'linux-s390x-binary-manywheel' }}
 
@@ -172,7 +172,6 @@ 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
 
@@ -185,7 +184,7 @@ jobs:
       - name: Checkout pytorch/builder to builder dir
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -216,12 +215,12 @@ jobs:
           path: "${{ runner.temp }}/artifacts/"
 
       - name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
-        uses: pytorch/test-infra/.github/actions/setup-nvidia@main
+        uses: pytorch/test-infra/.github/actions/setup-nvidia@release/2.5
         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@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ inputs.DOCKER_IMAGE }}
 
@@ -231,7 +230,7 @@ jobs:
 
       - name: Teardown Linux
         if: always() && inputs.build_environment != 'linux-s390x-binary-manywheel'
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
 
       - 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@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           no-sudo: true
 

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

@@ -28,7 +28,7 @@ jobs:
       keep-going: ${{ steps.filter.outputs.keep-going }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: false
@@ -49,7 +49,7 @@ jobs:
     runs-on: ${{ matrix.runner }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Set up JDK 8
         uses: actions/setup-java@v3
@@ -58,7 +58,7 @@ jobs:
           distribution: 'temurin'
 
       - name: Setup miniconda
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.5
         with:
           python-version: 3.8
           environment-file: .github/requirements/conda-env-${{ runner.os }}-${{ runner.arch }}

.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@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         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@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - 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@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ inputs.docker-image }}
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         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@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()

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

@@ -46,7 +46,7 @@ jobs:
       keep-going: ${{ steps.filter.outputs.keep-going }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: false
@@ -80,7 +80,7 @@ jobs:
     steps:
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Populate CI build options
         shell: bash
@@ -102,7 +102,7 @@ jobs:
             brew install libtool
 
       - name: Setup miniconda for iOS
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.5
         with:
           python-version: "3.9"
           environment-file: .github/requirements/conda-env-iOS.txt

.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@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
 
@@ -117,7 +117,7 @@ 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@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Setup Linux
         uses: ./.github/actions/setup-linux
@@ -132,7 +132,7 @@ jobs:
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ inputs.docker-image-name }}
 
@@ -146,7 +146,7 @@ jobs:
           echo "docker pull ghcr.io/pytorch/ci-image:${tag/:/-}"
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
@@ -269,5 +269,5 @@ jobs:
           s3-bucket: ${{ inputs.s3-bucket }}
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()

.github/workflows/_linux-test.yml

@@ -72,7 +72,7 @@ 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@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         if: ${{ !contains(matrix.runner, 'gcp.a100') }}
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -81,7 +81,7 @@ jobs:
               docker exec -it $(docker container ps --format '{{.ID}}') bash
 
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Setup Linux
         uses: ./.github/actions/setup-linux
@@ -96,7 +96,7 @@ jobs:
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ inputs.docker-image }}
 
@@ -110,7 +110,7 @@ jobs:
           echo "docker pull ghcr.io/pytorch/ci-image:${tag/:/-}"
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
@@ -121,7 +121,7 @@ jobs:
 
       - name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
         id: install-nvidia-driver
-        uses: pytorch/test-infra/.github/actions/setup-nvidia@main
+        uses: pytorch/test-infra/.github/actions/setup-nvidia@release/2.5
         if: ${{ contains(inputs.build-environment, 'cuda') && !contains(matrix.config, 'nogpu') && steps.check_arc_runner.outputs.IN_ARC_RUNNER == 'false' }}
 
       - name: Lock NVIDIA A100 40GB Frequency
@@ -342,7 +342,7 @@ jobs:
           path: ./**/core.[1-9]*
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()
 
       # 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@main
+        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.5
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - 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@main
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.5
         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@main
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.5
         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@main
+        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.5

.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@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
 
@@ -82,7 +82,7 @@ jobs:
           use-gha: true
 
       - name: Setup miniconda
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.5
         with:
           python-version: ${{ inputs.python-version }}
           environment-file: .github/requirements/conda-env-${{ runner.os }}-${{ runner.arch }}
@@ -161,4 +161,4 @@ jobs:
       - name: Clean up disk space
         if: always()
         continue-on-error: true
-        uses: pytorch/test-infra/.github/actions/check-disk-space@main
+        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.5

.github/workflows/_mac-test.yml

@@ -74,11 +74,11 @@ jobs:
           done
 
       - name: Clean up disk space before running MacOS workflow
-        uses: pytorch/test-infra/.github/actions/check-disk-space@main
+        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.5
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Download build artifacts
         uses: ./.github/actions/download-build-artifacts
@@ -93,7 +93,7 @@ jobs:
           use-gha: true
 
       - name: Setup miniconda
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.5
         with:
           python-version: ${{ inputs.python-version }}
           environment-file: .github/requirements/conda-env-${{ runner.os }}-${{ runner.arch }}
@@ -217,4 +217,4 @@ jobs:
       - name: Clean up disk space
         if: always()
         continue-on-error: true
-        uses: pytorch/test-infra/.github/actions/check-disk-space@main
+        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.5

.github/workflows/_rocm-test.yml

@@ -58,7 +58,7 @@ jobs:
     steps:
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           no-sudo: true
 
@@ -80,12 +80,12 @@ jobs:
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ inputs.docker-image }}
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 

.github/workflows/_run_android_tests.yml

@@ -28,7 +28,7 @@ jobs:
       keep-going: ${{ steps.filter.outputs.keep-going }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: false
@@ -59,10 +59,10 @@ jobs:
       SUPPORT_ABI: '${{ matrix.support_abi }}'
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Setup miniconda
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.5
         with:
           python-version: 3.8
           environment-file: .github/requirements/conda-env-${{ runner.os }}-${{ runner.arch }}.txt

.github/workflows/_runner-determinator.yml

@@ -45,7 +45,7 @@ jobs:
       ISSUE_OWNER: ${{ inputs.issue_owner }}
     steps:
       # - name: Checkout PyTorch
-      #   uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+      #   uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
       #   with:
       #     fetch-depth: 1
       #     submodules: true

.github/workflows/_win-build.yml

@@ -79,10 +79,10 @@ jobs:
           git config --global core.fsmonitor false
 
       - name: Clean up leftover processes on non-ephemeral Windows runner
-        uses: pytorch/test-infra/.github/actions/cleanup-runner@main
+        uses: pytorch/test-infra/.github/actions/cleanup-runner@release/2.5
 
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
           instructions: |
@@ -97,7 +97,7 @@ jobs:
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           no-sudo: true
 

.github/workflows/_win-test.yml

@@ -57,10 +57,10 @@ jobs:
           git config --global core.fsmonitor false
 
       - name: Clean up leftover processes on non-ephemeral Windows runner
-        uses: pytorch/test-infra/.github/actions/cleanup-runner@main
+        uses: pytorch/test-infra/.github/actions/cleanup-runner@release/2.5
 
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
           instructions: |
@@ -76,7 +76,7 @@ jobs:
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           no-sudo: true
 

.github/workflows/_xpu-test.yml

@@ -54,7 +54,7 @@ jobs:
     steps:
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Setup XPU
         uses: ./.github/actions/setup-xpu
@@ -72,12 +72,12 @@ jobs:
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ inputs.docker-image }}
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 

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

@@ -40,12 +40,12 @@ jobs:
       CUDA_VERSION: ${{ matrix.cuda_version }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: conda-builder${{ matrix.cuda_version == 'cpu' && '-' || '-cuda' }}${{matrix.cuda_version}}
             docker-build-dir:  .ci/docker/conda

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

@@ -40,12 +40,12 @@ jobs:
       GPU_ARCH_VERSION: ${{ matrix.cuda_version }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: libtorch-cxx11-builder-cuda${{matrix.cuda_version}}
             docker-build-dir:  .ci/docker/libtorch
@@ -75,12 +75,12 @@ jobs:
       GPU_ARCH_VERSION: ${{ matrix.rocm_version }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: libtorch-cxx11-builder-rocm${{matrix.rocm_version}}
             docker-build-dir:  .ci/docker/libtorch
@@ -104,12 +104,12 @@ jobs:
     runs-on: linux.9xlarge.ephemeral
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: libtorch-cxx11-builder-cpu
             docker-build-dir:  .ci/docker/libtorch

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

@@ -27,6 +27,7 @@ env:
   DOCKER_REGISTRY: "docker.io"
   DOCKER_BUILDKIT: 1
   WITH_PUSH: ${{ github.event_name == 'push' && (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release')) }}
+  WITH_PUSH_ROCM: ${{ github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v') }}
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}
@@ -46,12 +47,12 @@ jobs:
       - name: Purge tools folder (free space for build)
         run: rm -rf /opt/hostedtoolcache
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinux-builder-cuda${{matrix.cuda_version}}
             docker-build-dir:  .ci/docker/manywheel
@@ -84,12 +85,12 @@ jobs:
       - name: Purge tools folder (free space for build)
         run: rm -rf /opt/hostedtoolcache
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinux2_28-builder-cuda${{matrix.cuda_version}}
             docker-build-dir:  .ci/docker/manywheel
@@ -122,7 +123,7 @@ jobs:
         uses: actions/checkout@v3
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinuxaarch64-builder-cuda${{matrix.cuda_version}}
             docker-build-dir:  .ci/docker/manywheel
@@ -152,28 +153,28 @@ jobs:
       GPU_ARCH_VERSION: ${{ matrix.rocm_version }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
-        if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        if: env.WITH_PUSH_ROCM == 'false'
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinux-builder-rocm${{matrix.rocm_version}}
             docker-build-dir:  .ci/docker/manywheel
             always-rebuild: true
             push: true
-      - name: Authenticate if WITH_PUSH
-        if: env.WITH_PUSH == 'true'
+      - name: Authenticate if WITH_PUSH_ROCM
+        if: env.WITH_PUSH_ROCM == 'true'
         env:
           DOCKER_TOKEN: ${{ secrets.DOCKER_TOKEN }}
           DOCKER_ID: ${{ secrets.DOCKER_ID }}
         run: |
-          if [[ "${WITH_PUSH}" == true ]]; then
+          if [[ "${WITH_PUSH_ROCM}" == true ]]; then
             echo "${DOCKER_TOKEN}" | docker login -u "${DOCKER_ID}" --password-stdin
           fi
       - name: Build Docker Image
-        if: env.WITH_PUSH == 'true'
+        if: env.WITH_PUSH_ROCM == 'true'
         run: |
           .ci/docker/manywheel/build.sh manylinux-builder:rocm${{matrix.rocm_version}}
   build-docker-cpu:
@@ -181,12 +182,12 @@ jobs:
     runs-on: am2.linux.9xlarge.ephemeral
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinux-builder-cpu
             docker-build-dir:  .ci/docker/manywheel
@@ -212,12 +213,12 @@ jobs:
       GPU_ARCH_TYPE: cpu-manylinux_2_28
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinux2_28-builder-cpu
             docker-build-dir:  .ci/docker/manywheel
@@ -243,12 +244,12 @@ jobs:
       GPU_ARCH_TYPE: cpu-aarch64
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinuxaarch64-builder-cpu-aarch64
             docker-build-dir:  .ci/docker/manywheel
@@ -274,12 +275,12 @@ jobs:
       GPU_ARCH_TYPE: cpu-aarch64-2_28
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinux2_28_aarch64-builder-cpu-aarch64
             docker-build-dir:  .ci/docker/manywheel
@@ -308,12 +309,12 @@ jobs:
       GPU_ARCH_TYPE: cpu-cxx11-abi
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinuxcxx11-abi-builder-cpu-cxx11-abi
             docker-build-dir:  .ci/docker/manywheel
@@ -339,12 +340,12 @@ jobs:
       GPU_ARCH_TYPE: xpu
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
       - name: Calculate docker image
         if: env.WITH_PUSH == 'false'
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
             docker-image-name: manylinux2_28-builder-xpu
             docker-build-dir:  .ci/docker/manywheel

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

@@ -47,12 +47,12 @@ jobs:
       BUILD_DEVICE: ${{ matrix.device }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
 
@@ -60,7 +60,7 @@ jobs:
         uses: ./.github/actions/setup-linux
 
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ env.DOCKER_IMAGE }}
 
@@ -125,7 +125,7 @@ jobs:
           path: ${{ runner.temp }}/artifacts/*
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()
 
   upload-wheel:
@@ -210,12 +210,12 @@ jobs:
       PY_VERS: ${{ matrix.py_vers }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
 
@@ -223,7 +223,7 @@ jobs:
         uses: ./.github/actions/setup-linux
 
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ env.DOCKER_IMAGE }}
 
@@ -258,7 +258,7 @@ jobs:
           path: ${{ runner.temp }}/artifacts/*
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()
 
   upload-conda:

.github/workflows/check-labels.yml

@@ -35,7 +35,7 @@ jobs:
     runs-on: linux.20_04.4x
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
           fetch-depth: 1

.github/workflows/close-nonexistent-disable-issues.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Run close_nonexistent_disable_issues.py
         env:

.github/workflows/create_release.yml

@@ -63,7 +63,7 @@ jobs:
           files: ${{env.PT_RELEASE_FILE}}
       - name: Upload source distribution to GHA artifacts for release tags
         if: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') && contains(github.ref, 'rc') }}
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4.4.0
         with:
           name: ${{ env.PT_RELEASE_FILE }}
           path: ${{ env.PT_RELEASE_FILE }}

.github/workflows/docker-builds.yml

@@ -82,28 +82,28 @@ jobs:
       # [see note: pytorch repo ref]
       # deep clone (fetch-depth 0) required for git merge-base
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Setup Linux
         uses: ./.github/actions/setup-linux
 
       - name: Build docker image
         id: build-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: ${{ matrix.docker-image-name }}
           always-rebuild: true
           push: true
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.build-docker-image.outputs.docker-image }}
 
       - uses: nick-fields/retry@v3.0.0
         name: Push to https://https://ghcr.io/
         id: push-to-ghcr-io
-        if: ${{ github.event_name == 'push' }}
+        if: ${{ 0 && github.event_name == 'push' }}
         env:
           ECR_DOCKER_IMAGE: ${{ steps.build-docker-image.outputs.docker-image }}
           GHCR_PAT: ${{ secrets.GHCR_PAT }}
@@ -128,5 +128,5 @@ jobs:
         if: always()
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()

.github/workflows/docker-release.yml

@@ -41,7 +41,7 @@ jobs:
       matrix: ${{ steps.generate-matrix.outputs.matrix }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: true
@@ -69,7 +69,7 @@ jobs:
       CUDNN_VERSION: ${{ matrix.cudnn_version }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
       # [see note: pytorch repo ref]
@@ -147,12 +147,12 @@ jobs:
           fi
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()
 
   validate:
     needs: build
-    uses: pytorch/builder/.github/workflows/validate-docker-images.yml@main
+    uses: pytorch/builder/.github/workflows/validate-docker-images.yml@release/2.5
     with:
       channel: nightly
       ref: main

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

@@ -57,7 +57,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       runs_on: linux.arm64.m7g.4xlarge.ephemeral
@@ -81,7 +81,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu-aarch64
@@ -104,7 +104,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu-aarch64
@@ -126,7 +126,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cu124
       GPU_ARCH_TYPE: cuda-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-2.5
       DESIRED_DEVTOOLSET: cxx11-abi
       use_split_build: False
       DESIRED_PYTHON: "3.9"
@@ -151,7 +151,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cu124
       GPU_ARCH_TYPE: cuda-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-2.5
       DESIRED_DEVTOOLSET: cxx11-abi
       use_split_build: False
       DESIRED_PYTHON: "3.9"
@@ -174,7 +174,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.10"
       runs_on: linux.arm64.m7g.4xlarge.ephemeral
@@ -198,7 +198,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu-aarch64
@@ -221,7 +221,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu-aarch64
@@ -243,7 +243,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cu124
       GPU_ARCH_TYPE: cuda-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-2.5
       DESIRED_DEVTOOLSET: cxx11-abi
       use_split_build: False
       DESIRED_PYTHON: "3.10"
@@ -268,7 +268,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cu124
       GPU_ARCH_TYPE: cuda-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-2.5
       DESIRED_DEVTOOLSET: cxx11-abi
       use_split_build: False
       DESIRED_PYTHON: "3.10"
@@ -291,7 +291,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.11"
       runs_on: linux.arm64.m7g.4xlarge.ephemeral
@@ -315,7 +315,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu-aarch64
@@ -338,7 +338,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu-aarch64
@@ -360,7 +360,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cu124
       GPU_ARCH_TYPE: cuda-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-2.5
       DESIRED_DEVTOOLSET: cxx11-abi
       use_split_build: False
       DESIRED_PYTHON: "3.11"
@@ -385,7 +385,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cu124
       GPU_ARCH_TYPE: cuda-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-2.5
       DESIRED_DEVTOOLSET: cxx11-abi
       use_split_build: False
       DESIRED_PYTHON: "3.11"
@@ -408,7 +408,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.12"
       runs_on: linux.arm64.m7g.4xlarge.ephemeral
@@ -432,7 +432,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu-aarch64
@@ -455,7 +455,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu-aarch64
@@ -477,7 +477,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cu124
       GPU_ARCH_TYPE: cuda-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-2.5
       DESIRED_DEVTOOLSET: cxx11-abi
       use_split_build: False
       DESIRED_PYTHON: "3.12"
@@ -502,7 +502,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cu124
       GPU_ARCH_TYPE: cuda-aarch64
-      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-2.5
       DESIRED_DEVTOOLSET: cxx11-abi
       use_split_build: False
       DESIRED_PYTHON: "3.12"

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

@@ -57,7 +57,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: conda-py3_9-cpu
@@ -78,7 +78,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cpu
       build_environment: linux-binary-conda
@@ -100,7 +100,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cpu
     secrets:
@@ -122,7 +122,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -145,7 +145,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda11_8
       build_environment: linux-binary-conda
@@ -168,7 +168,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda11_8
     secrets:
@@ -190,7 +190,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -213,7 +213,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda12_1
       build_environment: linux-binary-conda
@@ -236,7 +236,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda12_1
     secrets:
@@ -258,7 +258,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -281,7 +281,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda12_4
       build_environment: linux-binary-conda
@@ -304,7 +304,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda12_4
     secrets:
@@ -325,7 +325,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: conda-py3_10-cpu
@@ -346,7 +346,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cpu
       build_environment: linux-binary-conda
@@ -368,7 +368,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cpu
     secrets:
@@ -390,7 +390,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -413,7 +413,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda11_8
       build_environment: linux-binary-conda
@@ -436,7 +436,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda11_8
     secrets:
@@ -458,7 +458,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -481,7 +481,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda12_1
       build_environment: linux-binary-conda
@@ -504,7 +504,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda12_1
     secrets:
@@ -526,7 +526,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -549,7 +549,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda12_4
       build_environment: linux-binary-conda
@@ -572,7 +572,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda12_4
     secrets:
@@ -593,7 +593,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.11"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: conda-py3_11-cpu
@@ -614,7 +614,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cpu
       build_environment: linux-binary-conda
@@ -636,7 +636,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cpu
     secrets:
@@ -658,7 +658,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.11"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -681,7 +681,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda11_8
       build_environment: linux-binary-conda
@@ -704,7 +704,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda11_8
     secrets:
@@ -726,7 +726,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.11"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -749,7 +749,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda12_1
       build_environment: linux-binary-conda
@@ -772,7 +772,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda12_1
     secrets:
@@ -794,7 +794,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.11"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -817,7 +817,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda12_4
       build_environment: linux-binary-conda
@@ -840,7 +840,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda12_4
     secrets:
@@ -861,7 +861,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.12"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: conda-py3_12-cpu
@@ -882,7 +882,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cpu
       build_environment: linux-binary-conda
@@ -904,7 +904,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cpu
     secrets:
@@ -926,7 +926,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.12"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -949,7 +949,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda11_8
       build_environment: linux-binary-conda
@@ -972,7 +972,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda11_8
     secrets:
@@ -994,7 +994,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.12"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -1017,7 +1017,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda12_1
       build_environment: linux-binary-conda
@@ -1040,7 +1040,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda12_1
     secrets:
@@ -1062,7 +1062,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.12"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
@@ -1085,7 +1085,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda12_4
       build_environment: linux-binary-conda
@@ -1108,7 +1108,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda12_4
     secrets:

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

@@ -52,7 +52,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -74,7 +74,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cpu-shared-with-deps-cxx11-abi

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

@@ -57,7 +57,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -79,7 +79,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cpu-shared-with-deps-cxx11-abi
@@ -102,7 +102,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cpu-shared-with-deps-cxx11-abi
@@ -125,7 +125,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda11.8-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -148,7 +148,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda11.8-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda11_8-shared-with-deps-cxx11-abi
@@ -172,7 +172,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda11.8-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda11_8-shared-with-deps-cxx11-abi
@@ -195,7 +195,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -218,7 +218,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda12_1-shared-with-deps-cxx11-abi
@@ -242,7 +242,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda12_1-shared-with-deps-cxx11-abi
@@ -265,7 +265,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.4-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -288,7 +288,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.4-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda12_4-shared-with-deps-cxx11-abi
@@ -312,7 +312,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.4-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda12_4-shared-with-deps-cxx11-abi
@@ -335,7 +335,7 @@ jobs:
       DESIRED_CUDA: rocm6.1
       GPU_ARCH_VERSION: 6.1
       GPU_ARCH_TYPE: rocm
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.1-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -360,7 +360,7 @@ jobs:
       GPU_ARCH_VERSION: 6.1
       GPU_ARCH_TYPE: rocm
       SKIP_ALL_TESTS: 1
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.1-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
     steps:
@@ -374,7 +374,6 @@ jobs:
       - name: Checkout PyTorch
         uses: malfet/checkout@silent-checkout
         with:
-          ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
           submodules: recursive
           path: pytorch
           quiet-checkout: true
@@ -386,7 +385,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -400,9 +399,9 @@ jobs:
         run: |
           echo "GPU_FLAG=--device=/dev/mem --device=/dev/kfd --device=/dev/dri --group-add video --group-add daemon" >> "${GITHUB_ENV}"
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
-          docker-image: pytorch/libtorch-cxx11-builder:rocm6.1-main
+          docker-image: pytorch/libtorch-cxx11-builder:rocm6.1-2.5
       - name: Test Pytorch binary
         uses: ./pytorch/.github/actions/test-pytorch-binary
       - name: Teardown ROCm
@@ -422,7 +421,7 @@ jobs:
       DESIRED_CUDA: rocm6.1
       GPU_ARCH_VERSION: 6.1
       GPU_ARCH_TYPE: rocm
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.1-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-rocm6_1-shared-with-deps-cxx11-abi
@@ -445,7 +444,7 @@ jobs:
       DESIRED_CUDA: rocm6.2
       GPU_ARCH_VERSION: 6.2
       GPU_ARCH_TYPE: rocm
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.2-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.2-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -470,7 +469,7 @@ jobs:
       GPU_ARCH_VERSION: 6.2
       GPU_ARCH_TYPE: rocm
       SKIP_ALL_TESTS: 1
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.2-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.2-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
     steps:
@@ -484,7 +483,6 @@ jobs:
       - name: Checkout PyTorch
         uses: malfet/checkout@silent-checkout
         with:
-          ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
           submodules: recursive
           path: pytorch
           quiet-checkout: true
@@ -496,7 +494,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -510,9 +508,9 @@ jobs:
         run: |
           echo "GPU_FLAG=--device=/dev/mem --device=/dev/kfd --device=/dev/dri --group-add video --group-add daemon" >> "${GITHUB_ENV}"
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
-          docker-image: pytorch/libtorch-cxx11-builder:rocm6.2-main
+          docker-image: pytorch/libtorch-cxx11-builder:rocm6.2-2.5
       - name: Test Pytorch binary
         uses: ./pytorch/.github/actions/test-pytorch-binary
       - name: Teardown ROCm
@@ -532,7 +530,7 @@ jobs:
       DESIRED_CUDA: rocm6.2
       GPU_ARCH_VERSION: 6.2
       GPU_ARCH_TYPE: rocm
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.2-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.2-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-rocm6_2-shared-with-deps-cxx11-abi

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

@@ -52,7 +52,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -74,7 +74,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cpu-shared-with-deps-pre-cxx11

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

@@ -57,7 +57,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -79,7 +79,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cpu-shared-with-deps-pre-cxx11
@@ -102,7 +102,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cpu-shared-with-deps-pre-cxx11
@@ -125,7 +125,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -148,7 +148,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda11_8-shared-with-deps-pre-cxx11
@@ -172,7 +172,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda11_8-shared-with-deps-pre-cxx11
@@ -195,7 +195,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -218,7 +218,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda12_1-shared-with-deps-pre-cxx11
@@ -242,7 +242,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda12_1-shared-with-deps-pre-cxx11
@@ -265,7 +265,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -288,7 +288,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda12_4-shared-with-deps-pre-cxx11
@@ -312,7 +312,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda12_4-shared-with-deps-pre-cxx11
@@ -335,7 +335,7 @@ jobs:
       DESIRED_CUDA: rocm6.1
       GPU_ARCH_VERSION: 6.1
       GPU_ARCH_TYPE: rocm
-      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -360,7 +360,7 @@ jobs:
       GPU_ARCH_VERSION: 6.1
       GPU_ARCH_TYPE: rocm
       SKIP_ALL_TESTS: 1
-      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
     steps:
@@ -374,7 +374,6 @@ jobs:
       - name: Checkout PyTorch
         uses: malfet/checkout@silent-checkout
         with:
-          ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
           submodules: recursive
           path: pytorch
           quiet-checkout: true
@@ -386,7 +385,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -400,9 +399,9 @@ jobs:
         run: |
           echo "GPU_FLAG=--device=/dev/mem --device=/dev/kfd --device=/dev/dri --group-add video --group-add daemon" >> "${GITHUB_ENV}"
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
-          docker-image: pytorch/manylinux-builder:rocm6.1-main
+          docker-image: pytorch/manylinux-builder:rocm6.1-2.5
       - name: Test Pytorch binary
         uses: ./pytorch/.github/actions/test-pytorch-binary
       - name: Teardown ROCm
@@ -422,7 +421,7 @@ jobs:
       DESIRED_CUDA: rocm6.1
       GPU_ARCH_VERSION: 6.1
       GPU_ARCH_TYPE: rocm
-      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-rocm6_1-shared-with-deps-pre-cxx11
@@ -445,7 +444,7 @@ jobs:
       DESIRED_CUDA: rocm6.2
       GPU_ARCH_VERSION: 6.2
       GPU_ARCH_TYPE: rocm
-      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -470,7 +469,7 @@ jobs:
       GPU_ARCH_VERSION: 6.2
       GPU_ARCH_TYPE: rocm
       SKIP_ALL_TESTS: 1
-      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
     steps:
@@ -484,7 +483,6 @@ jobs:
       - name: Checkout PyTorch
         uses: malfet/checkout@silent-checkout
         with:
-          ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
           submodules: recursive
           path: pytorch
           quiet-checkout: true
@@ -496,7 +494,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -510,9 +508,9 @@ jobs:
         run: |
           echo "GPU_FLAG=--device=/dev/mem --device=/dev/kfd --device=/dev/dri --group-add video --group-add daemon" >> "${GITHUB_ENV}"
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
-          docker-image: pytorch/manylinux-builder:rocm6.2-main
+          docker-image: pytorch/manylinux-builder:rocm6.2-2.5
       - name: Test Pytorch binary
         uses: ./pytorch/.github/actions/test-pytorch-binary
       - name: Teardown ROCm
@@ -532,7 +530,7 @@ jobs:
       DESIRED_CUDA: rocm6.2
       GPU_ARCH_VERSION: 6.2
       GPU_ARCH_TYPE: rocm
-      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-rocm6_2-shared-with-deps-pre-cxx11

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

@@ -53,7 +53,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -77,7 +77,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda11_8
@@ -100,7 +100,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -124,7 +124,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_1
@@ -147,7 +147,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -171,7 +171,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_4

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

@@ -53,7 +53,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -77,7 +77,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda11_8
@@ -100,7 +100,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -124,7 +124,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_1
@@ -147,7 +147,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -171,7 +171,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_4

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

@@ -58,7 +58,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -82,7 +82,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda11_8
@@ -106,7 +106,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda11_8
@@ -129,7 +129,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -153,7 +153,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_1
@@ -177,7 +177,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_1
@@ -200,7 +200,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -224,7 +224,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_4
@@ -248,7 +248,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_4
@@ -270,7 +270,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -292,7 +292,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu
@@ -315,7 +315,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu
@@ -338,7 +338,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -362,7 +362,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda11_8
@@ -386,7 +386,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda11_8
@@ -409,7 +409,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -433,7 +433,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_1
@@ -457,7 +457,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_1
@@ -480,7 +480,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -503,7 +503,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_1-full
@@ -527,7 +527,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_1-full
@@ -550,7 +550,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -574,7 +574,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_4
@@ -598,7 +598,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_4
@@ -620,7 +620,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -642,7 +642,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu
@@ -665,7 +665,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu
@@ -688,7 +688,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -712,7 +712,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda11_8
@@ -736,7 +736,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda11_8
@@ -759,7 +759,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -783,7 +783,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda12_1
@@ -807,7 +807,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda12_1
@@ -830,7 +830,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -854,7 +854,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda12_4
@@ -878,7 +878,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda12_4
@@ -900,7 +900,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -922,7 +922,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu
@@ -945,7 +945,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu
@@ -968,7 +968,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -992,7 +992,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda11_8
@@ -1016,7 +1016,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda11_8
@@ -1039,7 +1039,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -1063,7 +1063,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda12_1
@@ -1087,7 +1087,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda12_1
@@ -1110,7 +1110,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -1134,7 +1134,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda12_4
@@ -1158,7 +1158,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda12_4
@@ -1180,7 +1180,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -1202,7 +1202,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu
@@ -1225,7 +1225,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu
@@ -1248,7 +1248,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -1272,7 +1272,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda11_8
@@ -1296,7 +1296,7 @@ jobs:
       DESIRED_CUDA: cu118
       GPU_ARCH_VERSION: 11.8
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda11_8
@@ -1319,7 +1319,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -1343,7 +1343,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda12_1
@@ -1367,7 +1367,7 @@ jobs:
       DESIRED_CUDA: cu121
       GPU_ARCH_VERSION: 12.1
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda12_1
@@ -1390,7 +1390,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -1414,7 +1414,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda12_4
@@ -1438,7 +1438,7 @@ jobs:
       DESIRED_CUDA: cu124
       GPU_ARCH_VERSION: 12.4
       GPU_ARCH_TYPE: cuda
-      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda12_4
@@ -1460,7 +1460,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
@@ -1482,7 +1482,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cpu
@@ -1505,7 +1505,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       use_split_build: True
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cpu

.github/workflows/generated-linux-s390x-binary-manywheel-nightly.yml

@@ -57,7 +57,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       runs_on: linux.s390x
@@ -81,7 +81,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu-s390x
@@ -104,7 +104,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu-s390x
@@ -126,7 +126,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.10"
       runs_on: linux.s390x
@@ -150,7 +150,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu-s390x
@@ -173,7 +173,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu-s390x
@@ -195,7 +195,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.11"
       runs_on: linux.s390x
@@ -219,7 +219,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu-s390x
@@ -242,7 +242,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu-s390x
@@ -264,7 +264,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.12"
       runs_on: linux.s390x
@@ -288,7 +288,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu-s390x
@@ -311,7 +311,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu-s390x
@@ -333,7 +333,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.13"
       runs_on: linux.s390x
@@ -357,7 +357,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cpu-s390x
@@ -380,7 +380,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu-s390x
-      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-main
+      DOCKER_IMAGE: pytorch/manylinuxs390x-builder:cpu-s390x-2.5
       use_split_build: False
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cpu-s390x

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

@@ -74,7 +74,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -86,7 +85,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -138,7 +137,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cpu
       use_s3: False
@@ -189,7 +188,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -201,7 +199,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -253,7 +251,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cpu
       use_s3: False
@@ -304,7 +302,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -316,7 +313,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -368,7 +365,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cpu
       use_s3: False
@@ -419,7 +416,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -431,7 +427,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -483,7 +479,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/conda-builder:cpu-main
+      DOCKER_IMAGE: pytorch/conda-builder:cpu-2.5
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cpu
       use_s3: False

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

@@ -78,7 +78,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -90,7 +89,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -142,7 +141,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-main
+      DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-2.5
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cpu-shared-with-deps-cxx11-abi

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

@@ -75,7 +75,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -87,7 +86,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -139,7 +138,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       DESIRED_PYTHON: "3.9"
       build_name: wheel-py3_9-cpu
       use_s3: False
@@ -191,7 +190,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -203,7 +201,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -255,7 +253,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       DESIRED_PYTHON: "3.10"
       build_name: wheel-py3_10-cpu
       use_s3: False
@@ -307,7 +305,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -319,7 +316,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -371,7 +368,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       DESIRED_PYTHON: "3.11"
       build_name: wheel-py3_11-cpu
       use_s3: False
@@ -423,7 +420,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -435,7 +431,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -487,7 +483,7 @@ jobs:
       #       favor of GPU_ARCH_VERSION
       DESIRED_CUDA: cpu
       GPU_ARCH_TYPE: cpu
-      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
+      DOCKER_IMAGE: pytorch/manylinux-builder:cpu-2.5
       DESIRED_PYTHON: "3.12"
       build_name: wheel-py3_12-cpu
       use_s3: False

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

@@ -71,7 +71,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -102,7 +102,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -114,7 +113,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -185,7 +184,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -221,7 +220,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -233,7 +231,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -317,7 +315,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -348,7 +346,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -360,7 +357,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -432,7 +429,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -468,7 +465,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -480,7 +476,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -565,7 +561,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -596,7 +592,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -608,7 +603,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -680,7 +675,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -716,7 +711,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -728,7 +722,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -813,7 +807,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -844,7 +838,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -856,7 +849,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -928,7 +921,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -964,7 +957,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -976,7 +968,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1060,7 +1052,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1091,7 +1083,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1103,7 +1094,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1174,7 +1165,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1210,7 +1201,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1222,7 +1212,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1306,7 +1296,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1337,7 +1327,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1349,7 +1338,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1421,7 +1410,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1457,7 +1446,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1469,7 +1457,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1554,7 +1542,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1585,7 +1573,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1597,7 +1584,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1669,7 +1656,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1705,7 +1692,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1717,7 +1703,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1802,7 +1788,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1833,7 +1819,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1845,7 +1830,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1917,7 +1902,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1953,7 +1938,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1965,7 +1949,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2049,7 +2033,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2080,7 +2064,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2092,7 +2075,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2163,7 +2146,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2199,7 +2182,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2211,7 +2193,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2295,7 +2277,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2326,7 +2308,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2338,7 +2319,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2410,7 +2391,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2446,7 +2427,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2458,7 +2438,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2543,7 +2523,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2574,7 +2554,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2586,7 +2565,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2658,7 +2637,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2694,7 +2673,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2706,7 +2684,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2791,7 +2769,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2822,7 +2800,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2834,7 +2811,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2906,7 +2883,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2942,7 +2919,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2954,7 +2930,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3038,7 +3014,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3069,7 +3045,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3081,7 +3056,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3152,7 +3127,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3188,7 +3163,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3200,7 +3174,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3284,7 +3258,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3315,7 +3289,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3327,7 +3300,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3399,7 +3372,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3435,7 +3408,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3447,7 +3419,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3532,7 +3504,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3563,7 +3535,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3575,7 +3546,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3647,7 +3618,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3683,7 +3654,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3695,7 +3665,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3780,7 +3750,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3811,7 +3781,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3823,7 +3792,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3895,7 +3864,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3931,7 +3900,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3943,7 +3911,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder

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

@@ -68,7 +68,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -99,7 +99,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -111,7 +110,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -186,7 +185,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -222,7 +221,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -234,7 +232,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder

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

@@ -75,7 +75,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -106,7 +106,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -118,7 +117,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -193,7 +192,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -229,7 +228,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -241,7 +239,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -333,7 +331,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -364,7 +362,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -376,7 +373,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -452,7 +449,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -488,7 +485,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -500,7 +496,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -593,7 +589,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -624,7 +620,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -636,7 +631,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -712,7 +707,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -748,7 +743,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -760,7 +754,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -853,7 +847,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -884,7 +878,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -896,7 +889,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -972,7 +965,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1008,7 +1001,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1020,7 +1012,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder

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

@@ -68,7 +68,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -99,7 +99,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -111,7 +110,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -186,7 +185,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -222,7 +221,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -234,7 +232,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder

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

@@ -75,7 +75,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -106,7 +106,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -118,7 +117,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -193,7 +192,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -229,7 +228,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -241,7 +239,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -333,7 +331,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -364,7 +362,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -376,7 +373,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -452,7 +449,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -488,7 +485,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -500,7 +496,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -593,7 +589,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -624,7 +620,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -636,7 +631,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -712,7 +707,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -748,7 +743,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -760,7 +754,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -853,7 +847,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -884,7 +878,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -896,7 +889,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -972,7 +965,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1008,7 +1001,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1020,7 +1012,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder

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

@@ -72,7 +72,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -103,7 +103,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -115,7 +114,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -186,7 +185,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -222,7 +221,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -234,7 +232,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -319,7 +317,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -350,7 +348,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -362,7 +359,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -434,7 +431,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -470,7 +467,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -482,7 +478,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -568,7 +564,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -599,7 +595,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -611,7 +606,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -683,7 +678,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -719,7 +714,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -731,7 +725,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -817,7 +811,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -848,7 +842,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -860,7 +853,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -932,7 +925,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -968,7 +961,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -980,7 +972,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1064,7 +1056,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1095,7 +1087,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1107,7 +1098,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1178,7 +1169,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1214,7 +1205,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1226,7 +1216,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1310,7 +1300,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1341,7 +1331,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1353,7 +1342,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1424,7 +1413,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1460,7 +1449,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1472,7 +1460,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1557,7 +1545,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1588,7 +1576,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1600,7 +1587,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1672,7 +1659,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1708,7 +1695,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1720,7 +1706,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1806,7 +1792,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1837,7 +1823,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1849,7 +1834,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -1921,7 +1906,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -1957,7 +1942,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -1969,7 +1953,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2055,7 +2039,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2086,7 +2070,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2098,7 +2081,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2170,7 +2153,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2206,7 +2189,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2218,7 +2200,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2302,7 +2284,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2333,7 +2315,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2345,7 +2326,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2416,7 +2397,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2452,7 +2433,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2464,7 +2444,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2548,7 +2528,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2579,7 +2559,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2591,7 +2570,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2662,7 +2641,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2698,7 +2677,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2710,7 +2688,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2795,7 +2773,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2826,7 +2804,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2838,7 +2815,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -2910,7 +2887,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -2946,7 +2923,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -2958,7 +2934,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3044,7 +3020,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3075,7 +3051,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3087,7 +3062,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3159,7 +3134,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3195,7 +3170,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3207,7 +3181,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3293,7 +3267,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3324,7 +3298,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3336,7 +3309,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3408,7 +3381,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3444,7 +3417,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3456,7 +3428,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3540,7 +3512,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3571,7 +3543,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3583,7 +3554,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3654,7 +3625,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3690,7 +3661,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3702,7 +3672,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3786,7 +3756,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3817,7 +3787,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3829,7 +3798,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -3900,7 +3869,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -3936,7 +3905,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -3948,7 +3916,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -4033,7 +4001,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -4064,7 +4032,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -4076,7 +4043,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -4148,7 +4115,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -4184,7 +4151,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -4196,7 +4162,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -4282,7 +4248,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -4313,7 +4279,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -4325,7 +4290,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -4397,7 +4362,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -4433,7 +4398,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -4445,7 +4409,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -4531,7 +4495,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -4562,7 +4526,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -4574,7 +4537,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -4646,7 +4609,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -4682,7 +4645,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -4694,7 +4656,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -4778,7 +4740,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -4809,7 +4771,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -4821,7 +4782,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder
@@ -4892,7 +4853,7 @@ jobs:
           echo "instance-type: $(get_ec2_metadata instance-type)"
           echo "system info $(uname -a)"
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@main
+        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.5
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -4928,7 +4889,6 @@ jobs:
       - name: Checkout PyTorch
         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
@@ -4940,7 +4900,7 @@ jobs:
       - name: Checkout pytorch/builder
         uses: malfet/checkout@silent-checkout
         with:
-          ref: main
+          ref: release/2.5
           submodules: recursive
           repository: pytorch/builder
           path: builder

.github/workflows/inductor-rocm.yml

@@ -22,11 +22,11 @@ concurrency:
 permissions: read-all
 
 jobs:
-  linux-focal-rocm6_1-py3_8-inductor-build:
-    name: rocm6.1-py3.8-inductor
+  linux-focal-rocm6_2-py3_10-inductor-build:
+    name: rocm6.2-py3.10-inductor
     uses: ./.github/workflows/_linux-build.yml
     with:
-      build-environment: linux-focal-rocm6.1-py3.8
+      build-environment: linux-focal-rocm6.2-py3.10
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       test-matrix: |
         { include: [
@@ -34,14 +34,14 @@ jobs:
           { config: "inductor", shard: 2, num_shards: 2, runner: "linux.rocm.gpu.2" },
         ]}
 
-  linux-focal-rocm6_1-py3_8-inductor-test:
+  linux-focal-rocm6_2-py3_10-inductor-test:
     permissions:
       id-token: write
       contents: read
-    name: rocm6.1-py3.8-inductor
+    name: rocm6.2-py3.10-inductor
     uses: ./.github/workflows/_rocm-test.yml
-    needs: linux-focal-rocm6_1-py3_8-inductor-build
+    needs: linux-focal-rocm6_2-py3_10-inductor-build
     with:
-      build-environment: linux-focal-rocm6.1-py3.8
-      docker-image: ${{ needs.linux-focal-rocm6_1-py3_8-inductor-build.outputs.docker-image }}
-      test-matrix:  ${{ needs.linux-focal-rocm6_1-py3_8-inductor-build.outputs.test-matrix }}
+      build-environment: linux-focal-rocm6.2-py3.10
+      docker-image: ${{ needs.linux-focal-rocm6_2-py3_10-inductor-build.outputs.docker-image }}
+      test-matrix:  ${{ needs.linux-focal-rocm6_2-py3_10-inductor-build.outputs.test-matrix }}

.github/workflows/lint-bc.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Run BC Lint Action
-        uses: pytorch/test-infra/.github/actions/bc-lint@main
+        uses: pytorch/test-infra/.github/actions/bc-lint@release/2.5
         with:
           repo: ${{ github.event.pull_request.head.repo.full_name }}
           base_sha: ${{ github.event.pull_request.base.sha }}

.github/workflows/lint.yml

@@ -24,7 +24,7 @@ jobs:
       curr_branch: ${{ github.head_ref || github.ref_name }}
 
   lintrunner-clang:
-    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@release/2.5
     needs: get-label-type
     with:
       timeout: 120
@@ -41,7 +41,7 @@ jobs:
         .github/scripts/lintrunner.sh
 
   lintrunner-noclang:
-    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@release/2.5
     needs: get-label-type
     with:
       timeout: 120
@@ -57,7 +57,7 @@ jobs:
         .github/scripts/lintrunner.sh
 
   quick-checks:
-    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@release/2.5
     needs: get-label-type
     with:
       runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
@@ -100,7 +100,7 @@ jobs:
     if: github.event_name == 'pull_request' && !contains(github.event.pull_request.labels.*.name, 'skip-pr-sanity-checks')
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
           fetch-depth: -1
@@ -113,7 +113,7 @@ jobs:
           bash .github/scripts/pr-sanity-check.sh
 
   workflow-checks:
-    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@release/2.5
     needs: get-label-type
     with:
       runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
@@ -127,6 +127,7 @@ jobs:
         conda activate "${CONDA_ENV}"
 
         # Regenerate workflows
+        export RELEASE_VERSION_TAG="2.5"
         .github/scripts/generate_ci_workflows.py
 
         RC=0
@@ -150,7 +151,7 @@ jobs:
         exit $RC
 
   toc:
-    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@release/2.5
     needs: get-label-type
     with:
       runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
@@ -189,7 +190,7 @@ jobs:
   test-tools:
     name: Test tools
     if: ${{ github.repository == 'pytorch/pytorch' }}
-    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@release/2.5
     needs: get-label-type
     with:
       runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
@@ -211,14 +212,14 @@ jobs:
     runs-on: linux.20_04.4x
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
           fetch-depth: 1
-      - name: Setup Python 3.8
+      - name: Setup Python 3.9
         uses: actions/setup-python@v4
         with:
-          python-version: '3.8'
+          python-version: '3.9'
           architecture: x64
           cache: pip
       - name: Install dependencies
@@ -241,7 +242,7 @@ jobs:
       # [see note: pytorch repo ref]
       # deep clone (fetch-depth 0) required, to allow us to use git log
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
           fetch-depth: 1

.github/workflows/llm_td_retrieval.yml

@@ -48,7 +48,7 @@ jobs:
           path: llm-target-determinator
 
       - name: Setup miniconda
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.5
         with:
           python-version: "3.9"
 
@@ -117,5 +117,5 @@ jobs:
           AWS_REGION: ""
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()

.github/workflows/nightly-rockset-uploads.yml

@@ -21,7 +21,7 @@ jobs:
     environment: upload-stats
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: false

.github/workflows/nightly.yml

@@ -56,7 +56,7 @@ jobs:
     if: ${{ github.event_name == 'schedule' }}
     steps:
       - name: update-vision-commit-hash
-        uses: pytorch/test-infra/.github/actions/update-commit-hash@main
+        uses: pytorch/test-infra/.github/actions/update-commit-hash@release/2.5
         with:
           repo-name: vision
           branch: main
@@ -71,7 +71,7 @@ jobs:
     if: ${{ github.event_name == 'schedule' }}
     steps:
       - name: update-audio-commit-hash
-        uses: pytorch/test-infra/.github/actions/update-commit-hash@main
+        uses: pytorch/test-infra/.github/actions/update-commit-hash@release/2.5
         with:
           repo-name: audio
           branch: main
@@ -86,7 +86,7 @@ jobs:
     if: ${{ github.event_name == 'schedule' }}
     steps:
       - name: update-executorch-commit-hash
-        uses: pytorch/test-infra/.github/actions/update-commit-hash@main
+        uses: pytorch/test-infra/.github/actions/update-commit-hash@release/2.5
         with:
           repo-name: executorch
           branch: main

.github/workflows/nitpicker.yml

@@ -19,7 +19,7 @@ jobs:
     if: ${{ github.event.pull_request.number != 26921 && github.repository_owner == 'pytorch' }}
     steps:
     - name: Checkout PyTorch
-      uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+      uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
     - uses: ethanis/nitpicker@v1
       with:
         nitpicks: '.github/nitpicks.yml'

.github/workflows/periodic.yml

@@ -214,7 +214,9 @@ jobs:
   # TODO: Figure out how to migrate this job to M1 runner
   ios-build-test:
     name: ios-build-test
-    if: github.event_name != 'schedule' || github.event.schedule == '45 0,8,16 * * 1-5' || github.event.schedule == '45 4 * * 0,6' || github.event.schedule == '29 8 * * *'
+    # Has been broken for a while, see https://github.com/pytorch/pytorch/issues/136284
+    # if: github.event_name != 'schedule' || github.event.schedule == '45 0,8,16 * * 1-5' || github.event.schedule == '45 4 * * 0,6' || github.event.schedule == '29 8 * * *'
+    if: false
     uses: ./.github/workflows/_ios-build-test.yml
     with:
       trigger-event: ${{ github.event_name }}
@@ -293,13 +295,13 @@ jobs:
       docker-image: ${{ needs.linux-vulkan-focal-py3_11-clang10-build.outputs.docker-image }}
       test-matrix: ${{ needs.linux-vulkan-focal-py3_11-clang10-build.outputs.test-matrix }}
 
-  linux-focal-rocm6_1-py3_8-build:
-    name: linux-focal-rocm6.1-py3.8
+  linux-focal-rocm6_2-py3_10-build:
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
-      build-environment: linux-focal-rocm6.1-py3.8
+      build-environment: linux-focal-rocm6.2-py3.10
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       test-matrix: |
         { include: [
@@ -308,19 +310,19 @@ jobs:
           { config: "distributed", shard: 3, num_shards: 3, runner: "linux.rocm.gpu" },
         ]}
 
-  linux-focal-rocm6_1-py3_8-test:
+  linux-focal-rocm6_2-py3_10-test:
     permissions:
       id-token: write
       contents: read
-    name: linux-focal-rocm6.1-py3.8
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_rocm-test.yml
     needs:
-      - linux-focal-rocm6_1-py3_8-build
+      - linux-focal-rocm6_2-py3_10-build
       - target-determination
     with:
-      build-environment: linux-focal-rocm6.1-py3.8
-      docker-image: ${{ needs.linux-focal-rocm6_1-py3_8-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-rocm6_1-py3_8-build.outputs.test-matrix }}
+      build-environment: linux-focal-rocm6.2-py3.10
+      docker-image: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.test-matrix }}
 
   linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build:
     name: linux-focal-cuda12.1-py3.10-gcc9-experimental-split-build

.github/workflows/pull.yml

@@ -503,15 +503,15 @@ jobs:
         ]}
     secrets: inherit
 
-  linux-focal-rocm6_1-py3_8-build:
+  linux-focal-rocm6_2-py3_10-build:
     # don't run build twice on main
     if: github.event_name == 'pull_request'
-    name: linux-focal-rocm6.1-py3.8
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
-      build-environment: linux-focal-rocm6.1-py3.8
+      build-environment: linux-focal-rocm6.2-py3.10
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       sync-tag: rocm-build
       test-matrix: |

.github/workflows/rocm.yml

@@ -31,11 +31,11 @@ jobs:
       id-token: write
       contents: read
 
-  linux-focal-rocm6_1-py3_8-build:
-    name: linux-focal-rocm6.1-py3.8
+  linux-focal-rocm6_2-py3_10-build:
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_linux-build.yml
     with:
-      build-environment: linux-focal-rocm6.1-py3.8
+      build-environment: linux-focal-rocm6.2-py3.10
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       sync-tag: rocm-build
       test-matrix: |
@@ -48,16 +48,16 @@ jobs:
           { config: "default", shard: 6, num_shards: 6, runner: "linux.rocm.gpu.2" },
         ]}
 
-  linux-focal-rocm6_1-py3_8-test:
+  linux-focal-rocm6_2-py3_10-test:
     permissions:
       id-token: write
       contents: read
-    name: linux-focal-rocm6.1-py3.8
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_rocm-test.yml
     needs:
-      - linux-focal-rocm6_1-py3_8-build
+      - linux-focal-rocm6_2-py3_10-build
       - target-determination
     with:
-      build-environment: linux-focal-rocm6.1-py3.8
-      docker-image: ${{ needs.linux-focal-rocm6_1-py3_8-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-rocm6_1-py3_8-build.outputs.test-matrix }}
+      build-environment: linux-focal-rocm6.2-py3.10
+      docker-image: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.test-matrix }}

.github/workflows/slow.yml

@@ -22,6 +22,7 @@ permissions: read-all
 
 jobs:
   llm-td:
+    if: false
     name: before-test
     uses: ./.github/workflows/llm_td_retrieval.yml
     permissions:
@@ -29,6 +30,7 @@ jobs:
       contents: read
 
   target-determination:
+    if: false
     name: before-test
     uses: ./.github/workflows/target_determination.yml
     needs: llm-td
@@ -37,6 +39,7 @@ jobs:
       contents: read
 
   get-label-type:
+    if: false
     name: get-label-type
     uses: ./.github/workflows/_runner-determinator.yml
     with:
@@ -46,6 +49,7 @@ jobs:
       curr_ref_type: ${{ github.ref_type }}
 
   linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build:
+    if: false
     name: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
@@ -56,15 +60,18 @@ jobs:
       cuda-arch-list: 8.6
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 2, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 3, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 4, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 5, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 6, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 8, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 2, num_shards: 8, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 3, num_shards: 8, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 4, num_shards: 8, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 5, num_shards: 8, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 6, num_shards: 8, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 7, num_shards: 8, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 8, num_shards: 8, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-test:
+    if: false
     name: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck
     uses: ./.github/workflows/_linux-test.yml
     needs:
@@ -77,6 +84,7 @@ jobs:
       timeout-minutes: 300
 
   linux-focal-cuda12_1-py3_10-gcc9-sm86-build:
+    if: false
     name: linux-focal-cuda12.1-py3.10-gcc9-sm86
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
@@ -87,11 +95,13 @@ jobs:
       cuda-arch-list: 8.6
       test-matrix: |
         { include: [
-          { config: "slow", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
-          { config: "slow", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "slow", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "slow", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "slow", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_1-py3_10-gcc9-sm86-test:
+    if: false
     name: linux-focal-cuda12.1-py3.10-gcc9-sm86
     uses: ./.github/workflows/_linux-test.yml
     needs:
@@ -103,6 +113,7 @@ jobs:
       test-matrix: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-sm86-build.outputs.test-matrix }}
 
   linux-focal-py3_9-clang10-build:
+    if: false
     name: linux-focal-py3.9-clang10
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
@@ -117,6 +128,7 @@ jobs:
         ]}
 
   linux-focal-py3_9-clang10-test:
+    if: false
     name: linux-focal-py3.9-clang10
     uses: ./.github/workflows/_linux-test.yml
     needs:
@@ -127,13 +139,14 @@ jobs:
       docker-image: ${{ needs.linux-focal-py3_9-clang10-build.outputs.docker-image }}
       test-matrix: ${{ needs.linux-focal-py3_9-clang10-build.outputs.test-matrix }}
 
-  linux-focal-rocm6_1-py3_8-build:
-    name: linux-focal-rocm6.1-py3.8
+  linux-focal-rocm6_2-py3_10-build:
+    if: false
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
-      build-environment: linux-focal-rocm6.1-py3.8
+      build-environment: linux-focal-rocm6.2-py3.10
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       test-matrix: |
         { include: [
@@ -141,21 +154,23 @@ jobs:
           { config: "slow", shard: 2, num_shards: 2, runner: "linux.rocm.gpu" },
         ]}
 
-  linux-focal-rocm6_1-py3_8-test:
+  linux-focal-rocm6_2-py3_10-test:
+    if: false
     permissions:
       id-token: write
       contents: read
-    name: linux-focal-rocm6.1-py3.8
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_rocm-test.yml
     needs:
-      - linux-focal-rocm6_1-py3_8-build
+      - linux-focal-rocm6_2-py3_10-build
       - target-determination
     with:
-      build-environment: linux-focal-rocm6.1-py3.8
-      docker-image: ${{ needs.linux-focal-rocm6_1-py3_8-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-rocm6_1-py3_8-build.outputs.test-matrix }}
+      build-environment: linux-focal-rocm6.2-py3.10
+      docker-image: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.test-matrix }}
 
   linux-jammy-py3_10-clang15-asan-build:
+    if: false
     name: linux-jammy-py3.10-clang15-asan
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
@@ -173,6 +188,7 @@ jobs:
     secrets: inherit
 
   linux-jammy-py3_10-clang15-asan-test:
+    if: false
     name: linux-jammy-py3.10-clang15-asan
     uses: ./.github/workflows/_linux-test.yml
     needs:

.github/workflows/target-determination-indexer.yml

@@ -24,7 +24,7 @@ jobs:
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.5
         with:
           docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
           working-directory: pytorch
@@ -39,13 +39,13 @@ jobs:
           echo "docker pull ghcr.io/pytorch/ci-image:${tag/:/-}"
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.5
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
       - name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
         id: install-nvidia-driver
-        uses: pytorch/test-infra/.github/actions/setup-nvidia@main
+        uses: pytorch/test-infra/.github/actions/setup-nvidia@release/2.5
 
       - name: Clone CodeLlama
         uses: actions/checkout@v3
@@ -136,7 +136,7 @@ jobs:
             "s3://target-determinator-assets/indexes/latest/${ZIP_NAME}"
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@main
+        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.5
         if: always()
 
 concurrency:

.github/workflows/target_determination.yml

@@ -25,7 +25,7 @@ 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@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
 

.github/workflows/trunk.yml

@@ -223,13 +223,13 @@ jobs:
       cuda-version: "12.1"
       runner: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
 
-  linux-focal-rocm6_1-py3_8-build:
-    name: linux-focal-rocm6.1-py3.8
+  linux-focal-rocm6_2-py3_10-build:
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
       runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
-      build-environment: linux-focal-rocm6.1-py3.8
+      build-environment: linux-focal-rocm6.2-py3.10
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       sync-tag: rocm-build
       test-matrix: |
@@ -240,19 +240,19 @@ jobs:
         ]}
     secrets: inherit
 
-  linux-focal-rocm6_1-py3_8-test:
+  linux-focal-rocm6_2-py3_10-test:
     permissions:
       id-token: write
       contents: read
-    name: linux-focal-rocm6.1-py3.8
+    name: linux-focal-rocm6.2-py3.10
     uses: ./.github/workflows/_rocm-test.yml
     needs:
-      - linux-focal-rocm6_1-py3_8-build
+      - linux-focal-rocm6_2-py3_10-build
       - target-determination
     with:
-      build-environment: linux-focal-rocm6.1-py3.8
-      docker-image: ${{ needs.linux-focal-rocm6_1-py3_8-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-rocm6_1-py3_8-build.outputs.test-matrix }}
+      build-environment: linux-focal-rocm6.2-py3.10
+      docker-image: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.test-matrix }}
       tests-to-include: "test_nn test_torch test_cuda test_ops test_unary_ufuncs test_binary_ufuncs test_autograd inductor/test_torchinductor distributed/test_c10d_common distributed/test_c10d_nccl"
 
   linux-focal-cuda12_4-py3_10-gcc9-experimental-split-build:

.github/workflows/update-viablestrict.yml

@@ -16,7 +16,7 @@ jobs:
     environment: ${{ (github.event_name == 'schedule') && 'mergebot' || '' }}
     steps:
       - name: Update viable/strict
-        uses: pytorch/test-infra/.github/actions/update-viablestrict@main
+        uses: pytorch/test-infra/.github/actions/update-viablestrict@release/2.5
         with:
           repository: pytorch/pytorch
           stable-branch: viable/strict

.github/workflows/update_pytorch_labels.yml

@@ -17,7 +17,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: false

.github/workflows/upload-alerts.yml

@@ -44,7 +44,7 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-        uses: pytorch/test-infra/.github/actions/upload-alerts@main
+        uses: pytorch/test-infra/.github/actions/upload-alerts@release/2.5
         with:
           alerts: '${{ steps.alert_creation_step.outputs.script-output }}'
           organization: "pytorch"

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

@@ -38,7 +38,7 @@ jobs:
         run: echo "${TRIGGERING_WORKFLOW}"
 
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
 
       - name: Configure aws credentials
         uses: aws-actions/configure-aws-credentials@v3

.github/workflows/upload-torch-dynamo-perf-stats.yml

@@ -31,7 +31,7 @@ jobs:
     name: Upload dynamo performance stats for ${{ github.event.workflow_run.id }}, attempt ${{ github.event.workflow_run.run_attempt }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           submodules: false
           fetch-depth: 1

.github/workflows/upload_test_stats_intermediate.yml

@@ -17,7 +17,7 @@ jobs:
     environment: upload-stats
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.5
         with:
           fetch-depth: 1
           submodules: false

.github/workflows/weekly.yml

@@ -21,7 +21,7 @@ jobs:
           fetch-depth: 0
       - name: update-xla-commit-hash
         continue-on-error: true
-        uses: pytorch/test-infra/.github/actions/update-commit-hash@main
+        uses: pytorch/test-infra/.github/actions/update-commit-hash@release/2.5
         with:
           repo-name: xla
           branch: master
@@ -30,7 +30,7 @@ jobs:
           updatebot-token: ${{ secrets.UPDATEBOT_TOKEN }}
           pytorchbot-token: ${{ secrets.GH_PYTORCHBOT_TOKEN }}
       - name: update-triton-commit-hash
-        uses: pytorch/test-infra/.github/actions/update-commit-hash@main
+        uses: pytorch/test-infra/.github/actions/update-commit-hash@release/2.5
         with:
           repo-owner: openai
           repo-name: triton

README.md

@@ -27,8 +27,8 @@ Our trunk health (Continuous Integration signals) can be found at [hud.pytorch.o
       - [NVIDIA CUDA Support](#nvidia-cuda-support)
       - [AMD ROCm Support](#amd-rocm-support)
       - [Intel GPU Support](#intel-gpu-support)
-    - [Install Dependencies](#install-dependencies)
     - [Get the PyTorch Source](#get-the-pytorch-source)
+    - [Install Dependencies](#install-dependencies)
     - [Install PyTorch](#install-pytorch)
       - [Adjust Build Options (Optional)](#adjust-build-options-optional)
   - [Docker Image](#docker-image)
@@ -161,9 +161,34 @@ They require JetPack 4.2 and above, and [@dusty-nv](https://github.com/dusty-nv)
 #### Prerequisites
 If you are installing from source, you will need:
 - Python 3.8 or later (for Linux, Python 3.8.1+ is needed)
-- A compiler that fully supports C++17, such as clang or gcc (gcc 9.4.0 or newer is required)
+- A compiler that fully supports C++17, such as clang or gcc (gcc 9.4.0 or newer is required, on Linux)
+- Visual Studio or Visual Studio Build Tool on Windows
 
-We highly recommend installing an [Anaconda](https://www.anaconda.com/download) environment. You will get a high-quality BLAS library (MKL) and you get controlled dependency versions regardless of your Linux distro.
+\* PyTorch CI uses Visual C++ BuildTools, which come with Visual Studio Enterprise,
+Professional, or Community Editions. You can also install the build tools from
+https://visualstudio.microsoft.com/visual-cpp-build-tools/. The build tools *do not*
+come with Visual Studio Code by default.
+
+\* We highly recommend installing an [Anaconda](https://www.anaconda.com/download) environment. You will get a high-quality BLAS library (MKL) and you get controlled dependency versions regardless of your Linux distro.
+
+An example of environment setup is shown below:
+
+* Linux:
+
+```bash
+$ source <CONDA_INSTALL_DIR>/bin/activate
+$ conda create -y -n <CONDA_NAME>
+$ conda activate <CONDA_NAME>
+```
+
+* Windows:
+
+```bash
+$ source <CONDA_INSTALL_DIR>\Scripts\activate.bat
+$ conda create -y -n <CONDA_NAME>
+$ conda activate <CONDA_NAME>
+$ call "C:\Program Files\Microsoft Visual Studio\<VERSION>\Community\VC\Auxiliary\Build\vcvarsall.bat" x64
+```
 
 ##### NVIDIA CUDA Support
 If you want to compile with CUDA support, [select a supported version of CUDA from our support matrix](https://pytorch.org/get-started/locally/), then install the following:
@@ -194,12 +219,23 @@ If you want to compile with Intel GPU support, follow these
 If you want to disable Intel GPU support, export the environment variable `USE_XPU=0`.
 Other potentially useful environment variables may be found in `setup.py`.
 
+#### Get the PyTorch Source
+```bash
+git clone --recursive https://github.com/pytorch/pytorch
+cd pytorch
+# if you are updating an existing checkout
+git submodule sync
+git submodule update --init --recursive
+```
+
 #### Install Dependencies
 
 **Common**
 
 ```bash
 conda install cmake ninja
+# Run this command on native Windows
+conda install rust
 # Run this command from the PyTorch directory after cloning the source code using the “Get the PyTorch Source“ section below
 pip install -r requirements.txt
 ```
@@ -235,15 +271,6 @@ pip install mkl-static mkl-include
 conda install -c conda-forge libuv=1.39
 ```
 
-#### Get the PyTorch Source
-```bash
-git clone --recursive https://github.com/pytorch/pytorch
-cd pytorch
-# if you are updating an existing checkout
-git submodule sync
-git submodule update --init --recursive
-```
-
 #### Install PyTorch
 **On Linux**
 
@@ -284,13 +311,6 @@ python3 setup.py develop
 
 **On Windows**
 
-Choose Correct Visual Studio Version.
-
-PyTorch CI uses Visual C++ BuildTools, which come with Visual Studio Enterprise,
-Professional, or Community Editions. You can also install the build tools from
-https://visualstudio.microsoft.com/visual-cpp-build-tools/. The build tools *do not*
-come with Visual Studio Code by default.
-
 If you want to build legacy python code, please refer to [Building on legacy code and CUDA](https://github.com/pytorch/pytorch/blob/main/CONTRIBUTING.md#building-on-legacy-code-and-cuda)
 
 **CPU-only builds**
@@ -298,7 +318,6 @@ If you want to build legacy python code, please refer to [Building on legacy cod
 In this mode PyTorch computations will run on your CPU, not your GPU
 
 ```cmd
-conda activate
 python setup.py develop
 ```
 

aten/src/ATen/Context.cpp

@@ -145,6 +145,14 @@ void Context::setSDPUseMath(bool e) {
   enabled_mathSDP = e;
 }
 
+bool Context::allowFP16BF16ReductionMathSDP() const {
+  return allow_fp16_bf16_reduction_mathSDP;
+}
+
+void Context::setAllowFP16BF16ReductionMathSDP(bool e) {
+  allow_fp16_bf16_reduction_mathSDP = e;
+}
+
 bool Context::userEnabledCuDNNSDP() const {
   return enabled_cudnnSDP;
 }

aten/src/ATen/Context.h

@@ -234,6 +234,9 @@ class TORCH_API Context {
   void setSDPUseCuDNN(bool);
   bool userEnabledCuDNNSDP() const;
 
+  void setAllowFP16BF16ReductionMathSDP(bool);
+  bool allowFP16BF16ReductionMathSDP() const;
+
   void setSDPUseOverrideable(bool);
   bool userEnabledOverrideableSDP() const;
 
@@ -390,6 +393,7 @@ class TORCH_API Context {
   bool enabled_mathSDP = true;
   bool enabled_cudnnSDP = true;
   bool enabled_overrideable = true;
+  bool allow_fp16_bf16_reduction_mathSDP = false;
 #ifdef USE_ROCM
   bool benchmark_cudnn = true;
 #else

aten/src/ATen/native/CPUBlas.cpp

@@ -1149,22 +1149,6 @@ void brgemm(
   "Half Brgemm is only supported on X64 when oneDNN ukernel is enabled and avx512_fp16 is supported");
 }
 
-void brgemm(
-    int64_t M,
-    int64_t N,
-    int64_t K,
-    int64_t ld_a,
-    int64_t ld_b,
-    int64_t ld_c,
-    const float alpha,
-    const float beta,
-    const at::BFloat16* A,
-    const at::BFloat16* B,
-    float* C) {
-  TORCH_CHECK(false,
-  "BFloat16 Brgemm is currently not supported");
-}
-
 void brgemm_release() {
 #if ONEDNN_UKERNEL_ENABLED && (defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC)))
   dnnl::ukernel::brgemm::release_hw_context();

aten/src/ATen/native/CPUBlas.h

@@ -192,12 +192,7 @@ void copy(int64_t n, const c10::complex<float> *x, int64_t incx, c10::complex<fl
 // C = alpha * SUM(A[i] x B[i]) + beta * C, i = 0 to batch size
 // A Base pointer to a tensor A.
 // B Base pointer to a tensor B.
-// Byte offsets vector of pairs of tensors A and B offsets for
-//     each batch. The number of batches must coincide with the
-//     `batch_size` value passed at object construction stage.
 // C Pointer to a tensor C (accumulation buffer).
-// scratchpad Pointer to a scratchpad buffer.
-// Currently, only brgemm with batch size = 1 will be used
 TORCH_API void brgemm(
     int64_t M,
     int64_t N,
@@ -211,19 +206,6 @@ TORCH_API void brgemm(
     const at::Half* B,
     float* C);
 
-TORCH_API void brgemm(
-    int64_t M,
-    int64_t N,
-    int64_t K,
-    int64_t ld_a,
-    int64_t ld_b,
-    int64_t ld_c,
-    const float alpha,
-    const float beta,
-    const at::BFloat16* A,
-    const at::BFloat16* B,
-    float* C);
-
 // Release brgemm hardware context
 void brgemm_release();
 

aten/src/ATen/native/ForeachUtils.h

@@ -128,10 +128,26 @@ inline bool _check_tensors_share_device_and_dtype(
 // corresponding tensors in tensor lists have the same sizes and strides.
 inline bool _check_tensors_share_sizes_and_strides(
     ArrayRef<TensorList> tensorLists) {
+  auto is_diff_stride = [](const IntArrayRef& size,
+                           const IntArrayRef& left_stride,
+                           const IntArrayRef& right_stride) -> bool {
+    const size_t size_size = size.size();
+    for (const auto dim : c10::irange(size_size)) {
+      if (size[dim] == 1)
+        continue;
+      if (left_stride[dim] != right_stride[dim]) {
+        return true;
+      }
+    }
+    return false;
+  };
   for (const auto i : c10::irange(1, tensorLists.size())) {
     for (const auto j : c10::irange(tensorLists[0].size())) {
       if (tensorLists[0][j].sizes() != tensorLists[i][j].sizes() ||
-          tensorLists[0][j].strides() != tensorLists[i][j].strides()) {
+          is_diff_stride(
+              tensorLists[0][j].sizes(),
+              tensorLists[0][j].strides(),
+              tensorLists[i][j].strides())) {
         return false;
       }
     }

aten/src/ATen/native/cpu/FlashAttentionKernel.cpp

@@ -16,7 +16,6 @@
 #else
 #include <ATen/ops/empty.h>
 #endif
-
 namespace at::native {
 
 namespace {
@@ -202,7 +201,97 @@ void reshape_attn_mask_to_4d(
                 .expand({attn_mask_size_0, attn_mask_size_1, qSize, kvSize});
 }
 
-template <typename scalar_t, typename mask_t, int64_t q_split_size, int64_t kv_split_size>
+template <typename scalar_t>
+inline void copy_value_with_pad(
+    const scalar_t* value_ptr,
+    scalar_t* dst_ptr,
+    int64_t rows,
+    int64_t cols,
+    int64_t prows,
+    int64_t pcols,
+    int64_t ldi) {
+  auto vec_size = at::vec::Vectorized<scalar_t>::size();
+  int64_t i = 0;
+  for (; i < rows; i++) {
+    int64_t j = 0;
+    for (; j < cols - (cols % vec_size); j += vec_size) {
+      auto vec_v =
+          at::vec::Vectorized<scalar_t>::loadu(value_ptr + i * ldi + j);
+      vec_v.store(dst_ptr + i * pcols + j);
+    }
+
+    if (j < cols) {
+      auto vec_v = at::vec::Vectorized<scalar_t>::loadu(
+          value_ptr + i * ldi + j, cols - j);
+      vec_v.store(dst_ptr + i * pcols + j, cols - j);
+    }
+
+    // col padding
+    auto psize = pcols - cols;
+    if (psize > 0) {
+      auto zero_vec = at::vec::Vectorized<scalar_t>(0);
+      int64_t pj = 0;
+      for (; pj < psize - (psize % vec_size); pj += vec_size) {
+        zero_vec.store(dst_ptr + i * pcols + cols + pj);
+      }
+      if (pj < psize) {
+        zero_vec.store(dst_ptr + i * pcols + cols + pj, psize - pj);
+      }
+    }
+  }
+  // row padding
+  for (; i < prows; i++) {
+    auto zero_vec = at::vec::Vectorized<scalar_t>(0);
+    int64_t j = 0;
+    for (; j < pcols - (pcols % vec_size); j += vec_size) {
+      zero_vec.store(dst_ptr + i * pcols + j);
+    }
+    if (j < pcols) {
+      zero_vec.store(dst_ptr + i * pcols + j, pcols - j);
+    }
+
+  }
+}
+
+template <typename scalar_t>
+inline void pad_remain_row_col_zero(
+    scalar_t* value_ptr,
+    int rows,
+    int cols,
+    int prows,
+    int pcols,
+    int ldi) {
+  auto psize = pcols - cols;
+  if (psize == 0 && prows == rows) {
+    return;
+  }
+  auto vec_size = at::vec::Vectorized<scalar_t>::size();
+  auto zero = at::vec::Vectorized<scalar_t>(0);
+  if (psize > 0) {
+    for (int i = 0; i < rows; i++) {
+      int j = 0;
+      for (; j < psize - (psize % vec_size); j += vec_size) {
+        zero.store(value_ptr + i * ldi + cols + j);
+      }
+      if (j < psize) {
+        zero.store(value_ptr + i * ldi + cols + j, psize - j);
+      }
+    }
+  }
+
+  for (int i = rows; i < prows; i++) {
+    int j = 0;
+    for (; j < pcols - (pcols % vec_size); j += vec_size) {
+      zero.store(value_ptr + i * ldi + j);
+    }
+    if (j < pcols) {
+      zero.store(value_ptr + i * ldi + j, pcols - j);
+    }
+  }
+
+}
+
+template <typename scalar_t, typename mask_t, int64_t q_split_size, int64_t kv_split_size, bool with_pack=false>
 void cpu_flash_attention(
     const Tensor& output,
     const Tensor& logsumexp,
@@ -278,21 +367,70 @@ void cpu_flash_attention(
 
   int64_t qSplitSize = q_split_size > qSize ? qSize : q_split_size;
   int64_t kvSplitSize = kv_split_size > kvSize ? kvSize : kv_split_size;
-  int64_t qSlice = (qSize - 1) / qSplitSize + 1;
+  int64_t qSlice = (qSize + qSplitSize - 1) / qSplitSize;
+  int64_t kvSlice = (kvSize + kvSplitSize - 1) / kvSplitSize;
+  int64_t kvTail = (kvSize - 1) % kvSplitSize + 1;
   int64_t num_thread = at::get_num_threads();
 
   const auto dtype = query.scalar_type();
   const auto accumulate_dtype = toOpMathType(dtype);
 
+  // Whether pack is needed
+  bool need_pack = false;
+  // Block size of packing B matrix
+  int64_t packb_size = 64;
+  // Use packb_size due to the limitation:
+  // oneDNN pack only supports output leading dimention being one of (16, 32, 48, 64)
+  // For instance,
+  // for q @ k.T [qSplitSize, headSize] * [headSize, kvSplitSize] = [qSplitSize, kvSplitSize],
+  // we need to split kvSplitSize with packb_size for packing k.T,
+  // for (q @ k.T) @ v [qSplitSize, kvSplitSize] x [kvSplitSize, headSize] -> [qSplitSize, headSize],
+  // we need to split headSize with packb_size for packing v
+  // TODO Simplify the check when oneDNN supports fused pack with transpose and has better performance
+  if (with_pack) {
+    need_pack = num_head >= 4 && headSize % packb_size == 0 && kvSize >= packb_size;
+    if (need_pack) {
+      float pack_size = batchSize * num_head * kvSize * headSize / 1024;
+      float gemm_size_per_thread =
+          (batchSize * num_head * qSlice + num_thread - 1) / num_thread *
+          qSplitSize * (is_causal ? qSize : kvSize) * headSize / 1024;
+      float gsize = gemm_size_per_thread / pack_size;
+      // When the number of gemm is much greater than the number of pack,
+      // the pack and padding overhead can be overlaped.
+      if (pack_size < 2688) {
+        need_pack = gsize >= 36 || (gsize >= 24 && headSize > packb_size);
+      } else if (pack_size < 16384) {
+        need_pack = gsize >= (is_causal ? 54 : 52);
+      } else {
+        need_pack = gsize >= (is_causal ? 54 : 40);
+      }
+    }
+  }
+
+  int64_t rHeadSize = need_pack ? (headSize + packb_size - 1) / packb_size * packb_size : headSize;
+  int64_t rkvSplitSize = need_pack ? (kvSplitSize + packb_size - 1) / packb_size * packb_size : kvSplitSize;
+  int64_t rkvTail = need_pack ? (kvTail + packb_size - 1) / packb_size * packb_size : kvTail;
+  int64_t rkvSize = kv_split_size > kvSize ? rkvTail : rkvSplitSize * kvSlice + rkvTail;
+
+  // oneDNN pack does not support odd K now, we need also pad odd K
+  bool headSize_even = headSize % 2 == 0;
+  int64_t eheadSize = need_pack && !headSize_even ? headSize + 1: headSize;
+  int64_t ekvSplitSize = need_pack && (kvSplitSize % 2 != 0) ? kvSplitSize + 1 : kvSplitSize;
+  int64_t ekvTail = need_pack && (kvTail % 2 != 0) ? kvTail + 1 : kvTail;
+
   // allocate per thread temp buf (accumulate type)
   int64_t size_per_thread =
-      /* qk     */ qSplitSize * kvSplitSize +
+      /* qk     */ qSplitSize * rkvSplitSize +
       /* qk_max */ qSplitSize +
       /* qk_sum */ qSplitSize +
-      /* dst    */ qSplitSize * headSize;
+      /* dst    */ qSplitSize * rHeadSize;
 
   at::Tensor buf = at::empty({num_thread, size_per_thread}, query.options().dtype(accumulate_dtype));
-  at::Tensor buf_reduced = at::empty({num_thread, qSplitSize, is_reduced_type ? kvSplitSize : 0}, query.options());
+  at::Tensor buf_reduced = at::empty(
+    {num_thread,
+     qSplitSize,
+     is_reduced_type ? ekvSplitSize : 0},
+     query.options());
 
   // Data ptrs
   const scalar_t* q_data = query.const_data_ptr<scalar_t>();
@@ -306,16 +444,128 @@ void cpu_flash_attention(
   accum_t* buf_data = buf.data_ptr<accum_t>();
   scalar_t* buf_reduced_data = is_reduced_type ? buf_reduced.data_ptr<scalar_t>() : nullptr;
 
+  // Buffer to store padding query
+  scalar_t* query_padding_ptr = nullptr;
+  std::unique_ptr<scalar_t[]> query_padding_data;
+  if (!headSize_even && need_pack) {
+    query_padding_data = std::make_unique<scalar_t[]>(num_thread * qSplitSize * eheadSize);
+    query_padding_ptr = query_padding_data.get();
+  }
+  // Buffer to store Key and Value after transforms
+  scalar_t* key_reorder_ptr = nullptr;
+  std::unique_ptr<scalar_t[]> key_reorder_data;
+  scalar_t* value_reorder_ptr = nullptr;
+  std::unique_ptr<scalar_t[]> value_reorder_data;
+  int kv_padding_size = (kvSize - 1) / kvSplitSize * ekvSplitSize + ekvTail;
+  if (need_pack) {
+    key_reorder_data = std::make_unique<scalar_t[]>(batchSize * num_head * eheadSize * rkvSize);
+    key_reorder_ptr = key_reorder_data.get();
+    value_reorder_data = std::make_unique<scalar_t[]>(batchSize * num_head * kv_padding_size * rHeadSize);
+    value_reorder_ptr = value_reorder_data.get();
+  }
+
+  // Reorder K, V
+  if (need_pack) {
+    at::parallel_for(0, batchSize * num_head * kvSlice, 1, [&](int64_t begin, int64_t end) {
+        int64_t i = 0, j = 0, l = 0, n = 0;
+        at::native::data_index_init(begin, i, batchSize, j, num_head, l, kvSlice);
+        std::unique_ptr<scalar_t[]> transpose_buffer = std::make_unique<scalar_t[]>(eheadSize * packb_size);
+        scalar_t* transpose_buffer_ptr = transpose_buffer.get();
+        std::unique_ptr<scalar_t[]> v_copy_buffer = std::make_unique<scalar_t[]>(ekvSplitSize * packb_size);
+        scalar_t* v_copy_buffer_ptr = v_copy_buffer.get();
+        for (const auto z : c10::irange(begin, end)) {
+          (void)z; // Suppress unused variable
+          n = l * kvSplitSize;
+          int64_t kvBlockSize = std::min(kvSplitSize, kvSize - n);
+          int64_t ekvBlockSize = kvBlockSize % 2 == 0 ? kvBlockSize : kvBlockSize + 1;
+
+          // Split kvSplitSize with packb_size
+          // [kvSplitSize, headSize] -> [div_up(kvSplitSize, packb_size), packb_size, headSize]
+          // Transpose [packb_size, headSize] -> [headSize, packb_size]
+          // Pack transposed buffer
+
+          for (int64_t b = 0; b < kvBlockSize; b += packb_size) {
+            bool tail = kvBlockSize - b < packb_size;
+            // TODO Use fused pack with transpose support when oneDNN supports such usage
+            utils::transpose<uint16_t>(
+                tail ? kvBlockSize - b : packb_size,
+                headSize,
+                /* src_ptr */
+                reinterpret_cast<const uint16_t*>(
+                    k_data + i * kStrideB + j * kStrideH + n * kStrideN +
+                    b * kStrideN),
+                /* ld_src */ kStrideN,
+                /* dst */ reinterpret_cast<uint16_t*>(transpose_buffer_ptr),
+                /* ld_dst */ packb_size);
+            // Pad [headSize, x] -> [eheadSize, x]
+            if (!headSize_even) {
+              pad_remain_row_col_zero<scalar_t>(
+                  transpose_buffer_ptr,
+                  headSize,
+                  packb_size,
+                  eheadSize,
+                  packb_size,
+                  packb_size);
+            }
+            // Pack
+            cpublas::pack(
+                /* K */ eheadSize,
+                /* N */ packb_size,
+                /* ld_in */ packb_size,
+                /* ld_out */ packb_size,
+                /* dt_in */ dtype,
+                /* dt_out */ dtype,
+                transpose_buffer_ptr,
+                key_reorder_ptr + i * num_head * eheadSize * rkvSize +
+                    j * eheadSize * rkvSize + n * eheadSize + b * eheadSize);
+          }
+
+          // Split headSize with packb_size
+          // [kvSplitSize, headSize] -> [kvSplitSize,  div_up(headSize, packb_size), packb_size]
+          for (int64_t b = 0; b < headSize; b += packb_size) {
+            // Do copy due to the limitation of input_ld of oneDNN pack:
+            // Regarding packing [K, N], only input_ld == N is supported
+            // TODO: remove the copy when pack supports input_ld >= N
+            copy_value_with_pad<scalar_t>(
+                v_data + i * vStrideB + j * vStrideH + n * vStrideN + b,
+                v_copy_buffer_ptr,
+                kvBlockSize,
+                (headSize - b < packb_size) ? headSize - b : packb_size,
+                ekvBlockSize,
+                packb_size,
+                vStrideN);
+            cpublas::pack(
+                ekvBlockSize,
+                packb_size,
+                packb_size,
+                packb_size,
+                dtype,
+                dtype,
+                v_copy_buffer_ptr,
+                value_reorder_ptr +
+                    i * num_head * kv_padding_size * rHeadSize +
+                    j * kv_padding_size * rHeadSize + n * rHeadSize +
+                    ekvBlockSize * b);
+          }
+          // Move to the next query
+          at::native::data_index_step(i, batchSize, j, num_head, l, kvSlice);
+        }
+      });
+  }
+
   at::parallel_for(0, batchSize * num_head * qSlice, 1, [&](int64_t begin, int64_t end) {
     int64_t i = 0, j = 0, k = 0;
     data_index_init(begin, i, batchSize, j, num_head, k, qSlice);
     int ompIdx = at::get_thread_num();
     accum_t* buf_ptr = buf_data + ompIdx * size_per_thread;
     accum_t* qk_data = buf_ptr;
-    accum_t* qk_max_data = qk_data + qSplitSize * kvSplitSize;
+    accum_t* qk_max_data = qk_data + qSplitSize * rkvSplitSize;
     accum_t* qk_sum_data = qk_max_data + qSplitSize;
     accum_t* dst_data = qk_sum_data + qSplitSize;
-    scalar_t* qk_reduced_data = is_reduced_type ? buf_reduced_data + ompIdx * qSplitSize * kvSplitSize : nullptr;
+    scalar_t* qk_reduced_data = is_reduced_type ? buf_reduced_data + ompIdx * qSplitSize * ekvSplitSize : nullptr;
+    scalar_t* query_t_padding_ptr = (!headSize_even && need_pack)
+            ? query_padding_ptr + ompIdx * qSplitSize * eheadSize
+            : nullptr;
 
     for (const auto z : c10::irange(begin, end)) {
       (void)z; // Suppress unused variable
@@ -327,10 +577,46 @@ void cpu_flash_attention(
       fill_stub(qk_sum_data,
           static_cast<accum_t>(0), qBlockSize);
       int64_t num_keys = is_causal ? std::min(m + qBlockSize, kvSize) : kvSize;
+      if (!headSize_even && need_pack) {
+        // Pad query if headSize is not even
+        // [qBlockSize, headSize] -> [qBlockSize, eheadSize]
+        copy_value_with_pad<scalar_t>(
+          q_data + i * qStrideB + j * qStrideH + m * qStrideM,
+          query_t_padding_ptr,
+          qBlockSize,
+          headSize,
+          qBlockSize,
+          eheadSize,
+          qStrideM
+        );
+      }
       for (int64_t n = 0; n < num_keys; n += kvSplitSize) {
         int64_t kvBlockSize = std::min(kvSplitSize, kvSize - n);
+        int64_t ekvBlockSize = (need_pack && kvBlockSize % 2 != 0) ? kvBlockSize + 1 : kvBlockSize;
+        int64_t rkvBlockSize = kvBlockSize == kvSplitSize ? rkvSplitSize : rkvTail;
         // Calculate scale * q @ k.T
-        cpublas::gemm(
+        if (need_pack) {
+          if constexpr (std::is_same_v<scalar_t, at::Half>) {
+            for (int64_t b = 0; b < kvBlockSize; b += packb_size) {
+              cpublas::brgemm(
+                  qBlockSize,
+                  packb_size,
+                  eheadSize,
+                  headSize_even ? qStrideM : eheadSize,
+                  packb_size,
+                  rkvBlockSize,
+                  1.f,
+                  0.f,
+                  !headSize_even
+                      ? query_t_padding_ptr
+                      : q_data + i * qStrideB + j * qStrideH + m * qStrideM,
+                  key_reorder_ptr + i * num_head * eheadSize * rkvSize +
+                      j * eheadSize * rkvSize + n * eheadSize + b * eheadSize,
+                  qk_data + b);
+            }
+          }
+        } else {
+          cpublas::gemm(
             TransposeType::Transpose,
             TransposeType::NoTranspose,
             kvBlockSize,
@@ -346,11 +632,12 @@ void cpu_flash_attention(
             static_cast<accum_t>(0),
             qk_data,
             kvBlockSize);
+        }
         // Apply causal mask, fill unused with -inf
         if (is_causal && num_keys - n <= kvSplitSize) {
           for (const auto row : c10::irange(qBlockSize)) {
             int64_t last_col = m + row - n;
-            accum_t* row_ptr = qk_data + row * kvBlockSize;
+            accum_t* row_ptr = qk_data + row * rkvBlockSize;
             fill_stub(row_ptr + last_col + 1,
                 -std::numeric_limits<accum_t>::infinity(),
                 kvBlockSize - last_col - 1);
@@ -363,29 +650,29 @@ void cpu_flash_attention(
           for (int64_t row = 0; row < qBlockSize; ++row) {
 #if __GNUC__ == 11 && __GNUC_MINOR__ >= 4 && defined(__ARM_FEATURE_SVE)
               _scale_attn_mask_fusion_kernel(
-                qk_data + row * kvBlockSize,
+                qk_data + row * rkvBlockSize,
                 mask_data + i * mStrideB + j * mStrideH +
                     (m + row) * mStrideM + (mStrideN == 0 ? 0 : n),
                 kvBlockSize,
-                qk_data + row * kvBlockSize,
+                qk_data + row * rkvBlockSize,
                 scaling_factor,
                 mStrideN == 0);
 #else
               if (mStrideN == 0) {
                 _scale_attn_mask_fusion_kernel</*is_stride_0*/ true>(
-                  qk_data + row * kvBlockSize,
+                  qk_data + row * rkvBlockSize,
                   mask_data + i * mStrideB + j * mStrideH +
                       (m + row) * mStrideM,
                   kvBlockSize,
-                  qk_data + row * kvBlockSize,
+                  qk_data + row * rkvBlockSize,
                   scaling_factor);
               } else {
                 _scale_attn_mask_fusion_kernel</*is_stride_0*/ false>(
-                  qk_data + row * kvBlockSize,
+                  qk_data + row * rkvBlockSize,
                   mask_data + i * mStrideB + j * mStrideH +
                       (m + row) * mStrideM + n,
                   kvBlockSize,
-                  qk_data + row * kvBlockSize,
+                  qk_data + row * rkvBlockSize,
                   scaling_factor);
               }
 #endif
@@ -398,28 +685,28 @@ void cpu_flash_attention(
             // max per row
             tmp_max = at::vec::reduce_all<accum_t>(
                 [](Vec& x, Vec& y) { return at::vec::maximum(x, y); },
-                qk_data + row * kvBlockSize,
+                qk_data + row * rkvBlockSize,
                 kvBlockSize);
           } else {
             // apply scaling factor and max per row in fusion
             _mul_reduce_max_fusion_kernel(
-                qk_data + row * kvBlockSize,
+                qk_data + row * rkvBlockSize,
                 scaling_factor,
                 kvBlockSize,
-                qk_data + row * kvBlockSize,
+                qk_data + row * rkvBlockSize,
                 tmp_max);
           }
           tmp_max = qk_max_data[row] > tmp_max ? qk_max_data[row] : tmp_max;
           if (tmp_max == -std::numeric_limits<accum_t>::infinity()) {
             // to avoid `nan = exp2f(-inf - (-inf))`
-            fill_stub(conditional_data_ptr(qk_data, qk_reduced_data) + row * kvBlockSize,
+            fill_stub(conditional_data_ptr(qk_data, qk_reduced_data) + row * ekvBlockSize,
               static_cast<scalar_t>(0), kvBlockSize);
           } else {
             tmp_sum = tmp_max;
             // qk <- exp(qk - max) and sum per row
             _exp_reduce_sum_fusion_kernel(
-                qk_data + row * kvBlockSize, kvBlockSize,
-                conditional_data_ptr(qk_data, qk_reduced_data) + row * kvBlockSize,
+                qk_data + row * rkvBlockSize, kvBlockSize,
+                conditional_data_ptr(qk_data, qk_reduced_data) + row * ekvBlockSize,
                 tmp_sum);
             // exp_tmp <- exp(max[row] - max)
             exp_tmp = std::exp(qk_max_data[row] - tmp_max);
@@ -431,12 +718,40 @@ void cpu_flash_attention(
             if (n > 0) {
               vec::map<accum_t>(
                 [exp_tmp](Vec x) { return x * Vec(exp_tmp); },
-                dst_data + row * headSize, dst_data + row * headSize, headSize);
+                dst_data + row * rHeadSize,
+                dst_data + row * rHeadSize,
+                headSize);
             }
           }
+          if (need_pack && kvBlockSize % 2 != 0) {
+            // Pad: [qSplitSize,kvSplitSize] -> [qSplitSize,kvSplitSize + 1]
+            *(qk_reduced_data + row * (1 + kvBlockSize) + kvBlockSize) = scalar_t(0);
+          }
         }
         // Calculate Softmax(q @ k.T) @ v
-        cpublas::gemm(
+        if (need_pack) {
+          int64_t psize = n / kvSplitSize * ekvSplitSize;
+          if constexpr (std::is_same_v<scalar_t, at::Half>) {
+            for (int64_t b = 0; b < headSize; b += packb_size) {
+              cpublas::brgemm(
+                  qBlockSize,
+                  packb_size,
+                  ekvBlockSize,
+                  ekvBlockSize,
+                  packb_size,
+                  rHeadSize,
+                  1.0,
+                  n == 0 ? 0.f : 1.f,
+                  qk_reduced_data,
+                  value_reorder_ptr +
+                      i * num_head * kv_padding_size * rHeadSize +
+                      j * kv_padding_size * rHeadSize + psize * rHeadSize +
+                      b * ekvBlockSize,
+                  dst_data + b);
+            }
+          }
+        } else {
+          cpublas::gemm(
             TransposeType::NoTranspose,
             TransposeType::NoTranspose,
             headSize,
@@ -451,6 +766,7 @@ void cpu_flash_attention(
             n == 0 ? static_cast<accum_t>(0) : static_cast<accum_t>(1),
             dst_data,
             headSize);
+        }
       }
 
       // dst <- dst / sum[row]
@@ -465,7 +781,7 @@ void cpu_flash_attention(
         vec::map<scalar_t>(
           [sum_reciprocal](Vec x) { return x * Vec(sum_reciprocal); },
           out_data + i * oStrideB + j * oStrideH + m * oStrideM + row * oStrideM,
-          dst_data + row * headSize,
+          dst_data + row * rHeadSize,
           headSize);
       }
       // Store logsumexp for backward
@@ -478,7 +794,9 @@ void cpu_flash_attention(
       data_index_step(i, batchSize, j, num_head, k, qSlice);
     }
   });
-
+  if (need_pack) {
+    cpublas::brgemm_release();
+  }
 }
 
 template <typename scalar_t, typename mask_t, int64_t q_split_size, int64_t kv_split_size>
@@ -826,6 +1144,13 @@ void cpu_flash_attention_backward(
       AT_PRIVATE_CASE_TYPE_USING_HINT(                     \
           at::ScalarType::Half, mask_t, __VA_ARGS__))
 
+#define FLASH_ATTENTION_KERNEL(FNAME, PACK, TYPE1, TYPE2, SEQ1, SEQ2, ...)   \
+  if (PACK) {                                                      \
+    FNAME<TYPE1, TYPE2, SEQ1, SEQ2, true>(__VA_ARGS__);            \
+  } else {                                                         \
+    FNAME<TYPE1, TYPE2, SEQ1, SEQ2>(__VA_ARGS__);                  \
+  }
+
 void flash_attention_kernel_impl(
     const Tensor& output,
     const Tensor& logsumexp,
@@ -838,33 +1163,37 @@ void flash_attention_kernel_impl(
     std::optional<double> scale) {
   auto q_seq_len = query.size(2);
 
+  // When q_seq_len and k_seq_len are long enough,
+  // cpu_flash_attention with pack has better performance.
+  bool could_pack = (query.scalar_type() == kHalf && cpublas::need_pack(kHalf));
+
   AT_DISPATCH_FLOATING_TYPES_AND2(kBFloat16, kHalf, query.scalar_type(), "flash_attention", [&] {
     if (!attn_mask.has_value()) {
       if (q_seq_len >= 768) {
-        cpu_flash_attention<scalar_t, scalar_t, 256, 512>(
+        FLASH_ATTENTION_KERNEL(cpu_flash_attention, could_pack, scalar_t, scalar_t, 256, 512,
           output, logsumexp, query, key, value,
           dropout_p, is_causal, attn_mask, scale);
       } else if (q_seq_len >= 192) {
-        cpu_flash_attention<scalar_t, scalar_t, 64, 512>(
+        FLASH_ATTENTION_KERNEL(cpu_flash_attention, could_pack, scalar_t, scalar_t, 64, 512,
           output, logsumexp, query, key, value,
           dropout_p, is_causal, attn_mask, scale);
       } else {
-        cpu_flash_attention<scalar_t, scalar_t, 32, 512>(
+        FLASH_ATTENTION_KERNEL(cpu_flash_attention, could_pack, scalar_t, scalar_t, 32, 512,
           output, logsumexp, query, key, value,
           dropout_p, is_causal, attn_mask, scale);
       }
     } else {
       AT_DISPATCH_MASK_TYPES(attn_mask.value().scalar_type(), "flash_attention_mask", [&]() {
         if (q_seq_len >= 768) {
-          cpu_flash_attention<scalar_t, mask_t, 256, 512>(
+          FLASH_ATTENTION_KERNEL(cpu_flash_attention, could_pack, scalar_t, mask_t, 256, 512,
             output, logsumexp, query, key, value,
             dropout_p, is_causal, attn_mask, scale);
         } else if (q_seq_len >= 192) {
-          cpu_flash_attention<scalar_t, mask_t, 64, 512>(
+          FLASH_ATTENTION_KERNEL(cpu_flash_attention, could_pack, scalar_t, mask_t, 64, 512,
             output, logsumexp, query, key, value,
             dropout_p, is_causal, attn_mask, scale);
         } else {
-          cpu_flash_attention<scalar_t, mask_t, 32, 512>(
+          FLASH_ATTENTION_KERNEL(cpu_flash_attention, could_pack, scalar_t, mask_t, 32, 512,
             output, logsumexp, query, key, value,
             dropout_p, is_causal, attn_mask, scale);
         }
@@ -873,6 +1202,8 @@ void flash_attention_kernel_impl(
   });
 }
 
+#undef FLASH_ATTENTION_KERNEL
+
 void flash_attention_backward_kernel_impl(
     const at::Tensor& grad_q,
     const at::Tensor& grad_k,

aten/src/ATen/native/cpu/utils.h

@@ -159,6 +159,12 @@ inline void transpose<float>(int64_t M, int64_t N, const float* src, int64_t ld_
   TORCH_CHECK(fbgemm::fbgemmSupportedCPU(), "Your CPU does not support FBGEMM.");
   fbgemm::transpose_simd<float>(M, N, src, ld_src, dst, ld_dst);
 }
+
+template <>
+inline void transpose<uint16_t>(int64_t M, int64_t N, const uint16_t* src, int64_t ld_src, uint16_t* dst, int64_t ld_dst) {
+  TORCH_CHECK(fbgemm::fbgemmSupportedCPU(), "Your CPU does not support FBGEMM.");
+  fbgemm::transpose_simd<uint16_t>(M, N, src, ld_src, dst, ld_dst);
+}
 #endif
 
 template <typename index_t, typename F>

aten/src/ATen/native/cudnn/MHA.cpp

@@ -22,6 +22,7 @@ void run_cudnn_SDP_fprop(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     Tensor& softmaxstats,
     Tensor& o,
     Tensor& dropoutseed,
@@ -43,6 +44,7 @@ void run_cudnn_SDP_bprop(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     const Tensor& o,
     const Tensor& dO,
     const Tensor& softmaxstats,
@@ -86,9 +88,9 @@ using graph_and_tensors = std::tuple<
     std::shared_ptr<fe::graph::Tensor_attributes>, // Q,
     std::shared_ptr<fe::graph::Tensor_attributes>, // K,
     std::shared_ptr<fe::graph::Tensor_attributes>, // V,
+    std::optional<std::shared_ptr<fe::graph::Tensor_attributes>>, // Bias
     std::shared_ptr<fe::graph::Tensor_attributes>, // Attn_scale,
     // TODO(eqy): additional options
-    // std::shared_ptr<fe::graph::Tensor_attributes>, // Bias,
     // std::shared_ptr<fe::graph::Tensor_attributes>, // SEQ_LEN_Q,
     // std::shared_ptr<fe::graph::Tensor_attributes>, // SEQ_LEN_KV,
     std::shared_ptr<fe::graph::Tensor_attributes>, // Seed,
@@ -104,7 +106,8 @@ using graph_and_tensors_backward = std::tuple<
     std::shared_ptr<fe::graph::Tensor_attributes>, // Q,
     std::shared_ptr<fe::graph::Tensor_attributes>, // K,
     std::shared_ptr<fe::graph::Tensor_attributes>, // V,
-    std::shared_ptr<fe::graph::Tensor_attributes>, // Attn_scale
+    std::optional<std::shared_ptr<fe::graph::Tensor_attributes>>, // Bias,
+    std::shared_ptr<fe::graph::Tensor_attributes>, // Attn_scale,
     std::shared_ptr<fe::graph::Tensor_attributes>, // Seed,
     std::shared_ptr<fe::graph::Tensor_attributes>, // Offset,
     std::shared_ptr<fe::graph::Tensor_attributes>, // O,
@@ -126,6 +129,8 @@ struct MHAParams {
   std::array<int, MAX_MHA_DIM> q_stride;
   std::array<int, MAX_MHA_DIM> k_stride;
   std::array<int, MAX_MHA_DIM> v_stride;
+  std::array<int, MAX_MHA_DIM> bias_dim;
+  std::array<int, MAX_MHA_DIM> bias_stride;
   int64_t b;
   int64_t h;
   int64_t s_q;
@@ -135,6 +140,9 @@ struct MHAParams {
   double dropout_probability;
   bool is_causal;
   bool return_softmaxstats;
+  // might be redundant if we take 0 dim/stride
+  // as signaling no-bias
+  bool has_attn_bias;
 };
 
 void setMHAParams(
@@ -148,6 +156,7 @@ void setMHAParams(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     double dropout_probability,
     bool is_causal,
     bool return_softmaxstats) {
@@ -166,6 +175,7 @@ void setMHAParams(
   params.dropout_probability = dropout_probability;
   params.is_causal = is_causal;
   params.return_softmaxstats = return_softmaxstats;
+  params.has_attn_bias = attn_bias.has_value();
   TORCH_INTERNAL_ASSERT(
       q.sizes().size() == MAX_MHA_DIM,
       "Q tensor has unexpected number of dims, please report a bug to PyTorch.");
@@ -190,6 +200,17 @@ void setMHAParams(
   std::copy(k.strides().begin(), k.strides().end(), params.k_stride.begin());
   std::copy(v.sizes().begin(), v.sizes().end(), params.v_dim.begin());
   std::copy(v.strides().begin(), v.strides().end(), params.v_stride.begin());
+  // uninit is OK as the struct is memset 0'd
+  if (params.has_attn_bias) {
+    std::copy(
+        attn_bias.value().sizes().begin(),
+        attn_bias.value().sizes().end(),
+        params.bias_dim.begin());
+    std::copy(
+        attn_bias.value().strides().begin(),
+        attn_bias.value().strides().end(),
+        params.bias_stride.begin());
+  }
 }
 
 struct MHACacheKeyWrapper : ParamsWrapper<MHAParams> {
@@ -203,6 +224,7 @@ struct MHACacheKeyWrapper : ParamsWrapper<MHAParams> {
       const Tensor& q,
       const Tensor& k,
       const Tensor& v,
+      const std::optional<Tensor>& attn_bias,
       double dropout_probability,
       bool is_causal,
       bool return_softmaxstats) {
@@ -217,6 +239,7 @@ struct MHACacheKeyWrapper : ParamsWrapper<MHAParams> {
         q,
         k,
         v,
+        attn_bias,
         dropout_probability,
         is_causal,
         return_softmaxstats);
@@ -285,6 +308,7 @@ auto build_graph_and_tensors(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     Tensor& softmaxstats,
     Tensor& o,
     Tensor& dropoutseed,
@@ -301,36 +325,6 @@ auto build_graph_and_tensors(
   mha_graph->set_io_data_type(dtype)
       .set_intermediate_data_type(fe::DataType_t::FLOAT)
       .set_compute_data_type(fe::DataType_t::FLOAT);
-  auto Q = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("Q")
-          .set_dim(std::vector<int64_t>(
-              q.sizes().data(), q.sizes().data() + q.sizes().size()))
-          .set_stride(fixSizeOneDimStrideSDPA(
-              q.sizes(),
-              std::vector<int64_t>(
-                  q.strides().data(),
-                  q.strides().data() + q.strides().size()))));
-  auto K = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("K")
-          .set_dim(std::vector<int64_t>(
-              k.sizes().data(), k.sizes().data() + k.sizes().size()))
-          .set_stride(fixSizeOneDimStrideSDPA(
-              k.sizes(),
-              std::vector<int64_t>(
-                  k.strides().data(),
-                  k.strides().data() + k.strides().size()))));
-  auto V = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("V")
-          .set_dim(std::vector<int64_t>(
-              v.sizes().data(), v.sizes().data() + v.sizes().size()))
-          .set_stride(fixSizeOneDimStrideSDPA(
-              v.sizes(),
-              std::vector<int64_t>(
-                  v.strides().data(),
-                  v.strides().data() + v.strides().size()))));
   auto attn_scale =
       mha_graph->tensor(fe::graph::Tensor_attributes()
                             .set_name("Attn_scale")
@@ -338,11 +332,6 @@ auto build_graph_and_tensors(
                             .set_stride({1, 1, 1, 1})
                             .set_is_pass_by_value(true)
                             .set_data_type(fe::DataType_t::FLOAT));
-  // TODO(eqy): support bias in the future in a follow-up PR
-  // auto bias = mha_graph->tensor(fe::graph::Tensor_attributes()
-  //                         .set_name("bias")
-  //                         .set_dim({b, 1, s_q, s_kv})
-  //                         .set_stride({s_q * s_kv, s_q * s_kv, s_kv, 1}));
   auto seed = mha_graph->tensor(fe::graph::Tensor_attributes()
                                     .set_name("Seed")
                                     .set_dim({1, 1, 1, 1})
@@ -360,11 +349,30 @@ auto build_graph_and_tensors(
           .set_causal_mask(is_causal)
           .set_attn_scale(attn_scale)
           .set_dropout(dropout_probability, seed, offset);
-  // Optional bias in flash attention is only supported 8.9.3 onwards
-  if (cudnnGetVersion() >= 8904) {
-    // scaled_dot_product_flash_attention_options.set_alibi_mask(true);
+  auto Q = mha_graph->tensor(
+      fe::graph::Tensor_attributes()
+          .set_name("Q")
+          .set_dim(q.sizes().vec())
+          .set_stride(fixSizeOneDimStrideSDPA(q.sizes(), q.strides().vec())));
+  auto K = mha_graph->tensor(
+      fe::graph::Tensor_attributes()
+          .set_name("K")
+          .set_dim(k.sizes().vec())
+          .set_stride(fixSizeOneDimStrideSDPA(k.sizes(), k.strides().vec())));
+  auto V = mha_graph->tensor(
+      fe::graph::Tensor_attributes()
+          .set_name("V")
+          .set_dim(v.sizes().vec())
+          .set_stride(fixSizeOneDimStrideSDPA(v.sizes(), v.strides().vec())));
+  std::optional<std::shared_ptr<fe::graph::Tensor_attributes>> bias;
+  if (attn_bias.has_value()) {
+    bias =
+        mha_graph->tensor(fe::graph::Tensor_attributes()
+                              .set_name("bias")
+                              .set_dim(attn_bias.value().sizes().vec())
+                              .set_stride(attn_bias.value().strides().vec()));
+    scaled_dot_product_flash_attention_options.set_bias(bias.value());
   }
-
   auto seq_q = mha_graph->tensor(fe::graph::Tensor_attributes()
                                      .set_name("Seq_q")
                                      .set_dim({b, 1, 1, 1})
@@ -376,20 +384,9 @@ auto build_graph_and_tensors(
                                       .set_stride({1, 1, 1, 1})
                                       .set_data_type(fe::DataType_t::INT32));
 
-  // if (cudnnGetVersion() >= 8903) {
-  //     scaled_dot_product_flash_attention_options.set_bias(bias)
-  //         .set_padding_mask(true)
-  //         .set_seq_len_q(seq_q)
-  //         .set_seq_len_kv(seq_kv);
-  // }
-
   auto [O, Stats] =
       mha_graph->sdpa(Q, K, V, scaled_dot_product_flash_attention_options);
-  O->set_output(true)
-      .set_dim(std::vector<int64_t>(
-          o.sizes().data(), o.sizes().data() + o.sizes().size()))
-      .set_stride(std::vector<int64_t>(
-          o.strides().data(), o.strides().data() + o.strides().size()));
+  O->set_output(true).set_dim(o.sizes().vec()).set_stride(o.strides().vec());
 
   if (Stats) {
     Stats->set_output(true).set_data_type(fe::DataType_t::FLOAT);
@@ -407,6 +404,7 @@ auto build_graph_and_tensors(
       std::move(Q),
       std::move(K),
       std::move(V),
+      std::move(bias),
       std::move(attn_scale),
       std::move(seed),
       std::move(offset),
@@ -427,6 +425,7 @@ auto build_graph_and_tensors_backward(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     const Tensor& o,
     const Tensor& dO,
     const Tensor& softmaxstats,
@@ -447,24 +446,6 @@ auto build_graph_and_tensors_backward(
   mha_graph->set_io_data_type(dtype)
       .set_intermediate_data_type(fe::DataType_t::FLOAT)
       .set_compute_data_type(fe::DataType_t::FLOAT);
-  auto Q = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("Q")
-          .set_dim(std::vector<int64_t>(q.sizes().begin(), q.sizes().end()))
-          .set_stride(
-              std::vector<int64_t>(q.strides().begin(), q.strides().end())));
-  auto K = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("K")
-          .set_dim(std::vector<int64_t>(k.sizes().begin(), k.sizes().end()))
-          .set_stride(
-              std::vector<int64_t>(k.strides().begin(), k.strides().end())));
-  auto V = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("V")
-          .set_dim(std::vector<int64_t>(v.sizes().begin(), v.sizes().end()))
-          .set_stride(
-              std::vector<int64_t>(v.strides().begin(), v.strides().end())));
   auto attn_scale =
       mha_graph->tensor(fe::graph::Tensor_attributes()
                             .set_name("Attn_scale")
@@ -472,6 +453,31 @@ auto build_graph_and_tensors_backward(
                             .set_stride({1, 1, 1, 1})
                             .set_is_pass_by_value(true)
                             .set_data_type(fe::DataType_t::FLOAT));
+  auto sdpa_backward_options = fe::graph::SDPA_backward_attributes()
+                                   .set_name("CUDNN_SDPA_BACKWARD")
+                                   .set_causal_mask(is_causal)
+                                   .set_attn_scale(attn_scale);
+  auto Q = mha_graph->tensor(fe::graph::Tensor_attributes()
+                                 .set_name("Q")
+                                 .set_dim(q.sizes().vec())
+                                 .set_stride(q.strides().vec()));
+  auto K = mha_graph->tensor(fe::graph::Tensor_attributes()
+                                 .set_name("K")
+                                 .set_dim(k.sizes().vec())
+                                 .set_stride(k.strides().vec()));
+  auto V = mha_graph->tensor(fe::graph::Tensor_attributes()
+                                 .set_name("V")
+                                 .set_dim(v.sizes().vec())
+                                 .set_stride(v.strides().vec()));
+  std::optional<std::shared_ptr<fe::graph::Tensor_attributes>> bias;
+  if (attn_bias.has_value()) {
+    bias =
+        mha_graph->tensor(fe::graph::Tensor_attributes()
+                              .set_name("bias")
+                              .set_dim(attn_bias.value().sizes().vec())
+                              .set_stride(attn_bias.value().strides().vec()));
+    sdpa_backward_options.set_bias(bias.value());
+  }
   auto Seed = mha_graph->tensor(fe::graph::Tensor_attributes()
                                     .set_name("Seed")
                                     .set_dim({1, 1, 1, 1})
@@ -482,47 +488,27 @@ auto build_graph_and_tensors_backward(
                                       .set_dim({1, 1, 1, 1})
                                       .set_stride({1, 1, 1, 1})
                                       .set_data_type(fe::DataType_t::INT32));
-  auto O = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("O")
-          .set_dim(std::vector<int64_t>(o.sizes().begin(), o.sizes().end()))
-          .set_stride(
-              std::vector<int64_t>(o.strides().begin(), o.strides().end())));
-  auto STATS = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("Stats")
-          .set_dim(std::vector<int64_t>(
-              softmaxstats.sizes().begin(), softmaxstats.sizes().end()))
-          .set_stride(std::vector<int64_t>(
-              softmaxstats.strides().begin(), softmaxstats.strides().end()))
-          .set_data_type(fe::DataType_t::FLOAT));
-  auto DO = mha_graph->tensor(
-      fe::graph::Tensor_attributes()
-          .set_name("DO")
-          .set_dim(std::vector<int64_t>(dO.sizes().begin(), dO.sizes().end()))
-          .set_stride(
-              std::vector<int64_t>(dO.strides().begin(), dO.strides().end())));
-  auto sdpa_backward_options = fe::graph::SDPA_backward_attributes()
-                                   .set_name("CUDNN_SDPA_BACKWARD")
-                                   .set_causal_mask(is_causal)
-                                   .set_attn_scale(attn_scale);
+  auto O = mha_graph->tensor(fe::graph::Tensor_attributes()
+                                 .set_name("O")
+                                 .set_dim(o.sizes().vec())
+                                 .set_stride(o.strides().vec()));
+  auto STATS = mha_graph->tensor(fe::graph::Tensor_attributes()
+                                     .set_name("Stats")
+                                     .set_dim(softmaxstats.sizes().vec())
+                                     .set_stride(softmaxstats.strides().vec())
+                                     .set_data_type(fe::DataType_t::FLOAT));
+  auto DO = mha_graph->tensor(fe::graph::Tensor_attributes()
+                                  .set_name("DO")
+                                  .set_dim(dO.sizes().vec())
+                                  .set_stride(dO.strides().vec()));
   if (dropout_probability != 0.0f) {
     sdpa_backward_options.set_dropout(dropout_probability, Seed, Offset);
   }
   auto [DQ, DK, DV] =
       mha_graph->sdpa_backward(Q, K, V, O, DO, STATS, sdpa_backward_options);
-  DQ->set_output(true)
-      .set_dim(std::vector<int64_t>(dQ.sizes().begin(), dQ.sizes().end()))
-      .set_stride(
-          std::vector<int64_t>(dQ.strides().begin(), dQ.strides().end()));
-  DK->set_output(true)
-      .set_dim(std::vector<int64_t>(dK.sizes().begin(), dK.sizes().end()))
-      .set_stride(
-          std::vector<int64_t>(dK.strides().begin(), dK.strides().end()));
-  DV->set_output(true)
-      .set_dim(std::vector<int64_t>(dV.sizes().begin(), dV.sizes().end()))
-      .set_stride(
-          std::vector<int64_t>(dV.strides().begin(), dV.strides().end()));
+  DQ->set_output(true).set_dim(dQ.sizes().vec()).set_stride(dQ.strides().vec());
+  DK->set_output(true).set_dim(dK.sizes().vec()).set_stride(dK.strides().vec());
+  DV->set_output(true).set_dim(dV.sizes().vec()).set_stride(dV.strides().vec());
   AT_CUDNN_FRONTEND_CHECK(mha_graph->validate());
   AT_CUDNN_FRONTEND_CHECK(mha_graph->build_operation_graph(handle));
   AT_CUDNN_FRONTEND_CHECK(
@@ -534,6 +520,7 @@ auto build_graph_and_tensors_backward(
       std::move(Q),
       std::move(K),
       std::move(V),
+      std::move(bias),
       std::move(attn_scale),
       std::move(Seed),
       std::move(Offset),
@@ -559,6 +546,7 @@ void run_cudnn_SDP_fprop(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     Tensor& softmaxstats,
     Tensor& o,
     Tensor& dropoutseed,
@@ -573,6 +561,11 @@ void run_cudnn_SDP_fprop(
     softmaxstats = at::empty({b, h, s_q}, q.options().dtype(kFloat));
   }
 
+  // do nothing if we got 0-element tensors
+  if (!q.numel() || !k.numel() || !v.numel()) {
+    return;
+  }
+
   auto key = MHACacheKeyWrapper(
       b,
       h,
@@ -583,6 +576,7 @@ void run_cudnn_SDP_fprop(
       q,
       k,
       v,
+      attn_bias,
       dropout_probability,
       is_causal,
       return_softmaxstats);
@@ -605,13 +599,14 @@ void run_cudnn_SDP_fprop(
         q,
         k,
         v,
+        attn_bias,
         softmaxstats,
         o,
         dropoutseed,
         dropoutoffset,
         handle);
   }
-  auto [mha_graph, Q, K, V, attn_scale, seed, offset, O, Stats] =
+  auto [mha_graph, Q, K, V, bias, attn_scale, seed, offset, O, Stats] =
       graph_and_tensors_values;
   std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*>
       variant_pack = {
@@ -619,13 +614,15 @@ void run_cudnn_SDP_fprop(
           {K, k.data_ptr()},
           {V, v.data_ptr()},
           {attn_scale, &scaling_factor},
-          //{bias, bias.data_ptr()},
           {seed, dropoutseed.data_ptr()},
           {offset, dropoutoffset.data_ptr()},
           {O, o.data_ptr()}};
   if (return_softmaxstats) {
     variant_pack[Stats] = softmaxstats.data_ptr();
   }
+  if (attn_bias.has_value()) {
+    variant_pack[bias.value()] = attn_bias.value().data_ptr();
+  }
   auto workspace_size = mha_graph->get_workspace_size();
   auto workspace_ptr =
       c10::cuda::CUDACachingAllocator::get()->allocate(workspace_size);
@@ -647,6 +644,7 @@ void run_cudnn_SDP_bprop(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     const Tensor& o,
     const Tensor& dO,
     const Tensor& softmaxstats,
@@ -655,6 +653,12 @@ void run_cudnn_SDP_bprop(
     Tensor& dV,
     const Tensor& dropoutseed,
     const Tensor& dropoutoffset) {
+  // do nothing if we got 0-element tensors
+  if (!q.numel() || !k.numel() || !v.numel() || !o.numel() || !dO.numel() ||
+      !softmaxstats.numel()) {
+    return;
+  }
+
   Tensor dO_ = dO;
   if (!dO.strides()[dO.strides().size() - 1]) {
     TORCH_WARN(
@@ -694,6 +698,7 @@ void run_cudnn_SDP_bprop(
       q,
       k,
       v,
+      attn_bias,
       dropout_probability,
       is_causal,
       true);
@@ -715,6 +720,7 @@ void run_cudnn_SDP_bprop(
         q,
         k,
         v,
+        attn_bias,
         o,
         dO_,
         softmaxstats,
@@ -726,8 +732,20 @@ void run_cudnn_SDP_bprop(
         handle);
   }
   auto
-      [mha_graph, Q, K, V, attn_scale, Seed, Offset, O, Do, Stats, Dq, Dk, Dv] =
-          graph_and_tensors_backward_values;
+      [mha_graph,
+       Q,
+       K,
+       V,
+       bias,
+       attn_scale,
+       Seed,
+       Offset,
+       O,
+       Do,
+       Stats,
+       Dq,
+       Dk,
+       Dv] = graph_and_tensors_backward_values;
   std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*>
       variant_pack = {// inputs
                       {Q, q.data_ptr()},
@@ -746,6 +764,9 @@ void run_cudnn_SDP_bprop(
     variant_pack[Seed] = dropoutseed.data_ptr();
     variant_pack[Offset] = dropoutoffset.data_ptr();
   }
+  if (attn_bias.has_value()) {
+    variant_pack[bias.value()] = attn_bias.value().data_ptr();
+  }
   auto workspace_size = mha_graph->get_workspace_size();
   auto workspace_ptr =
       c10::cuda::CUDACachingAllocator::get()->allocate(workspace_size);

aten/src/ATen/native/cudnn/MHA.h

@@ -18,6 +18,7 @@ void run_cudnn_SDP_fprop(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     Tensor& softmaxstats,
     Tensor& o,
     Tensor& dropoutseed,
@@ -36,6 +37,7 @@ void run_cudnn_SDP_bprop(
     const Tensor& q,
     const Tensor& k,
     const Tensor& v,
+    const std::optional<Tensor>& attn_bias,
     const Tensor& o,
     const Tensor& dO,
     const Tensor& softmaxstats,

aten/src/ATen/native/transformers/attention.cpp

@@ -536,6 +536,24 @@ std::optional<Tensor> convert_boolean_attn_mask(const std::optional<Tensor>& att
   // Otherwise, attn_mask represents an additive attention tensor
   return attn_mask;
 }
+
+// alternate version to workaround -inf issue with cuDNN
+// TODO(eqy): delete this when cuDNN -inf issue is resolved
+std::optional<Tensor> convert_boolean_attn_mask_cudnn(const std::optional<Tensor>& attn_mask, caffe2::TypeMeta dtype) {
+  // Pass through
+  if(!attn_mask.has_value()){
+    return std::nullopt;
+  }
+  // Convert boolean mask to additive mask; need to invert mask to indicate what
+  // to mask *out*.
+  if (attn_mask->dtype() == at::kBool) {
+    // TODO Use the max type of the input and output
+    return at::where(attn_mask->logical_not(), -65504.0, at::scalar_tensor(0.0, at::TensorOptions().dtype(dtype)));
+  }
+  // Otherwise, attn_mask represents an additive attention tensor
+  return attn_mask;
+}
+
 // Memory Efficient Attention requires a padded attn mask bias
 // This function pads the attn_mask bias to be a multiple of 16
 // Then slices the padded bias to the original size
@@ -698,15 +716,16 @@ Tensor scaled_dot_product_attention(
           query_, key, value, attn_mask_, dropout_p, is_causal, scale, enable_gqa);
   }
   sdp::SDPBackend backend = static_cast<sdp::SDPBackend>(choice_int);
-  std::optional<Tensor> attn_mask = convert_boolean_attn_mask(attn_mask_, query_.dtype());
   switch (backend) {
     case sdp::SDPBackend::cudnn_attention: {
+      std::optional<Tensor> attn_mask = convert_boolean_attn_mask_cudnn(attn_mask_, query_.dtype());
       bool compute_logsumexp = should_compute_logsumexp(query_, key, value);
       auto out_lse_softmax = at::_scaled_dot_product_cudnn_attention(
-          query_, key, value, attn_mask_, compute_logsumexp, dropout_p, is_causal, false /*return_debug_mask*/, scale);
+          query_, key, value, attn_mask, compute_logsumexp, dropout_p, is_causal, false /*return_debug_mask*/, scale);
       return std::get<0>(out_lse_softmax);
     }
     case sdp::SDPBackend::flash_attention: {
+      std::optional<Tensor> attn_mask = convert_boolean_attn_mask(attn_mask_, query_.dtype());
       if(query_.device().type() == DeviceType::CUDA){
         c10::SymInt og_size = query_.sym_size(-1);
         Tensor query_padded = pad_last_dim<8, false>(query_);
@@ -723,6 +742,7 @@ Tensor scaled_dot_product_attention(
           query_, key, value, dropout_p, is_causal, attn_mask, scale));
     }
     case sdp::SDPBackend::efficient_attention: {
+      std::optional<Tensor> attn_mask = convert_boolean_attn_mask(attn_mask_, query_.dtype());
       bool compute_logsumexp = should_compute_logsumexp(query_, key, value);
       if (attn_mask.has_value()) {
         attn_mask.value() = preprocess_mask(attn_mask.value(), query_, key, value);;
@@ -732,11 +752,13 @@ Tensor scaled_dot_product_attention(
       return std::get<0>(out_and_lse);
     }
     case sdp::SDPBackend::overrideable: {
+      std::optional<Tensor> attn_mask = convert_boolean_attn_mask(attn_mask_, query_.dtype());
       auto out_lse_softmax = at::_scaled_dot_product_fused_attention_overrideable(
           query_, key, value, attn_mask, dropout_p, is_causal, false /*return_debug_mask*/, scale);
       return std::get<0>(out_lse_softmax);
     }
-    case sdp::SDPBackend::math:
+    case sdp::SDPBackend::math: {
+      std::optional<Tensor> attn_mask = convert_boolean_attn_mask(attn_mask_, query_.dtype());
       if ((!GradMode::is_enabled() || (!query_.requires_grad() && !key.requires_grad() && !value.requires_grad()))
           && query_.device().type() == DeviceType::MPS && dropout_p == 0.0
           && query_.is_contiguous() && key.is_contiguous() && value.is_contiguous()
@@ -761,6 +783,7 @@ Tensor scaled_dot_product_attention(
           std::nullopt, /*dropout_mask*/
           scale,
           enable_gqa));
+    }
     default:
       TORCH_CHECK(
           false,
@@ -780,22 +803,26 @@ std::tuple<Tensor, Tensor> _scaled_dot_product_attention_math(
             value.is_contiguous(),
         "scaled_dot_product_attention: If inputs are nested tensors they must be contiguous");
   }
+  auto& ctx = at::globalContext();
   auto origin_dtype = query_.scalar_type();
   // Keep query, key, value in high precision for accuracy
   // NestedTensor reports issues for backward with autograd so disabled: must be
   // contiguous to get buffer.
-  auto query_acc = (query_.scalar_type() == at::kHalf ||
-                    query_.scalar_type() == at::kBFloat16) &&
+  auto query_acc = !ctx.allowFP16BF16ReductionMathSDP() &&
+          (query_.scalar_type() == at::kHalf ||
+           query_.scalar_type() == at::kBFloat16) &&
           !query_.is_nested()
       ? query_.to(at::kFloat)
       : query_;
-  auto key_acc =
-      (key.scalar_type() == at::kHalf || key.scalar_type() == at::kBFloat16) &&
+  auto key_acc = !ctx.allowFP16BF16ReductionMathSDP() &&
+          (key.scalar_type() == at::kHalf ||
+           key.scalar_type() == at::kBFloat16) &&
           !key.is_nested()
       ? key.to(at::kFloat)
       : key;
-  auto value_acc = (value.scalar_type() == at::kHalf ||
-                    value.scalar_type() == at::kBFloat16) &&
+  auto value_acc = !ctx.allowFP16BF16ReductionMathSDP() &&
+          (value.scalar_type() == at::kHalf ||
+           value.scalar_type() == at::kBFloat16) &&
           !value.is_nested()
       ? value.to(at::kFloat)
       : value;

aten/src/ATen/native/transformers/cuda/attention.cu

@@ -774,6 +774,18 @@ std::tuple<Tensor, Tensor, Tensor, Tensor, c10::SymInt, c10::SymInt, Tensor, Ten
   TORCH_CHECK(
       max_seqlen_batch_k == max_seqlen_batch_v,
       "Key and Value must have the same sequence length");
+  auto attn_bias_ = attn_bias;
+  if (attn_bias_.has_value()) {
+    const auto bias_dim = attn_bias_.value().dim();
+    if (bias_dim == 2) {
+      attn_bias_ = attn_bias_.value().expand({batch_size, 1, max_seqlen_batch_q, max_seqlen_batch_k});
+    } else if (bias_dim == 3) {
+      attn_bias_ = attn_bias_.value().expand({batch_size, 1, max_seqlen_batch_q, max_seqlen_batch_k});
+    } else {
+      attn_bias_ = attn_bias_.value().expand({batch_size, attn_bias_.value().size(1), max_seqlen_batch_q, max_seqlen_batch_k});
+      TORCH_CHECK(bias_dim == 4, "cuDNN SDPA expects either a 2D, 3D, or 4D attn_bias but got ", attn_bias_.value().dim(), "D");
+    }
+  }
 
   Tensor attention, log_sumexp;
 
@@ -818,13 +830,14 @@ std::tuple<Tensor, Tensor, Tensor, Tensor, c10::SymInt, c10::SymInt, Tensor, Ten
                       query/* Tensor q*/,
                       key/* Tensor k*/,
                       value/* Tensor v*/,
+                      attn_bias_ /* std::optional<Tensor> */,
                       log_sumexp/*Tensor softmaxstats*/,
                       attention/*Tensor o*/,
                       cudnn_seed/*Tensor dropoutseed*/,
                       cudnn_offset/*Tensor dropoutoffset*/);
 
   // TODO(eqy): support debug_attn_mask
-  return std::make_tuple(attention, log_sumexp, Tensor(), Tensor(), max_seqlen_batch_q, max_seqlen_batch_k, cudnn_seed, cudnn_offset, Tensor());
+  return std::make_tuple(std::move(attention), std::move(log_sumexp), Tensor(), Tensor(), max_seqlen_batch_q, max_seqlen_batch_k, std::move(cudnn_seed), std::move(cudnn_offset), Tensor());
 }
 
 std::tuple<Tensor, Tensor, Tensor, Tensor> _scaled_dot_product_efficient_attention_cuda(
@@ -1102,10 +1115,13 @@ std::tuple<Tensor, Tensor, Tensor, Tensor, c10::SymInt, c10::SymInt> _efficient_
       offset_t = at::empty({}, at::dtype(at::kLong).device(device));
     } else {
       auto [seed, offset] = at::cuda::philox::unpack(philox_state);
-      seed_t = at::scalar_tensor(
-          at::Scalar(static_cast<int64_t>(seed)), at::dtype(at::kLong));
-      offset_t = at::scalar_tensor(
-          at::Scalar(static_cast<int64_t>(offset)), at::dtype(at::kLong));
+#ifdef USE_ROCM
+      const auto options = at::dtype(at::kLong).device(at::kCUDA);
+#else
+      const auto options = at::dtype(at::kLong);
+#endif
+      seed_t = at::scalar_tensor(at::Scalar(static_cast<int64_t>(seed)), options);
+      offset_t = at::scalar_tensor(at::Scalar(static_cast<int64_t>(offset)), options);
     }
   } else {
     // Not using dropout
@@ -1118,7 +1134,8 @@ std::tuple<Tensor, Tensor, Tensor, Tensor, c10::SymInt, c10::SymInt> _efficient_
   auto ret = aotriton::v2::flash::check_gpu(stream);
   if (hipSuccess != ret) {
       TORCH_CHECK(false,
-                  "[AOTriton] Accelerated SDPA only supports MI200/MI300X GPUs (gfx90a:sramecc+:xnack- or gfx94a:sramecc+:xnack-)")
+                  "[AOTriton] Accelerated SDPA only supports MI200/MI300X/Navi31 GPUs"
+                  " (gfx90a:sramecc+:xnack-/gfx942:sramecc+:xnack-/gfx1100)")
   }
 
   // AOTriton may accept aligned on logsumexp tensor in the future for better
@@ -1147,8 +1164,16 @@ std::tuple<Tensor, Tensor, Tensor, Tensor, c10::SymInt, c10::SymInt> _efficient_
 
   using aotriton::v2::flash::attn_fwd;
   using sdp::aotriton_adapter::mk_aotensor;
+  using sdp::aotriton_adapter::mk_aoscalartensor;
+  using sdp::aotriton_adapter::mk_philoxtensor;
   aotriton::TensorView<4> empty_t4(0, {0, 0, 0, 0}, {0, 0, 0, 0}, aotriton::DType::kFloat16);
   at::Tensor softmax_fa_t = at::empty({ 0, 0, 0, 0 }, query.options());
+  const bool use_philox_state = in_capture_stream;
+  auto seed = use_philox_state ? mk_philoxtensor(philox_state.seed_.ptr) : mk_aoscalartensor(seed_t);
+  auto offset1 = use_philox_state ? mk_philoxtensor(philox_state.offset_.ptr) : mk_aoscalartensor(offset_t);
+  auto offset2 = use_philox_state ? philox_state.offset_intragraph_ : 0;
+  auto seed_output = use_philox_state ? mk_philoxtensor(seed_t.data_ptr<int64_t>()) : mk_philoxtensor(nullptr);
+  auto offset_output = use_philox_state ? mk_philoxtensor(offset_t.data_ptr<int64_t>()) : mk_philoxtensor(nullptr);
   hipError_t err; // TODO: Error handling
   err = attn_fwd(mk_aotensor(q_t, "q"),
                  mk_aotensor(k_t, "k"),
@@ -1158,8 +1183,11 @@ std::tuple<Tensor, Tensor, Tensor, Tensor, c10::SymInt, c10::SymInt> _efficient_
                  mk_aotensor<2>(softmax_lse, "M"),
                  mk_aotensor(output_t, "Out"),
                  dropout_p,
-                 use_dropout ? *seed_t.data_ptr<int64_t>() : 0,
-                 use_dropout ? *offset_t.data_ptr<int64_t>() : 0,
+                 seed,
+                 offset1,
+                 offset2,
+                 seed_output,
+                 offset_output,
                  mk_aotensor(softmax_fa_t, "encoded_softmax"),
                  is_causal,
                  stream);