lint

.bazelversion

@@ -1 +1 @@
-6.5.0
+6.1.1

.buckconfig.oss

@@ -0,0 +1,23 @@
+[pt]
+  is_oss=1
+
+[buildfile]
+  name = BUCK.oss
+  includes = //tools/build_defs/select.bzl
+
+[repositories]
+  bazel_skylib = third_party/bazel-skylib/
+  ovr_config = .
+
+[download]
+  in_build = true
+
+[cxx]
+  cxxflags = -std=c++17
+  ldflags = -Wl,--no-undefined
+  should_remap_host_platform = true
+  cpp = /usr/bin/clang
+  cc = /usr/bin/clang
+  cxx = /usr/bin/clang++
+  cxxpp = /usr/bin/clang++
+  ld = /usr/bin/clang++

.ci/aarch64_linux/README.md

@@ -1,19 +0,0 @@
-# Aarch64 (ARM/Graviton) Support Scripts
-Scripts for building aarch64 PyTorch PIP Wheels. These scripts build the following wheels:
-* torch
-* torchvision
-* torchaudio
-* torchtext
-* torchdata
-## Aarch64_ci_build.sh
-This script is design to support CD operations within PyPi manylinux aarch64 container, and be executed in the container. It prepares the container and then executes __aarch64_wheel_ci_build.py__ to build the wheels. The script "assumes" the PyTorch repo is located at: ```/pytorch``` and will put the wheels into ```/artifacts```.
-### Usage
-```DESIRED_PYTHON=<PythonVersion> aarch64_ci_build.sh```
-
-__NOTE:__ CI build is currently __EXPERMINTAL__
-
-## Build_aarch64_wheel.py
-This app allows a person to build using AWS EC3 resources and requires AWS-CLI and Boto3 with AWS credentials to support building EC2 instances for the wheel builds. Can be used in a codebuild CD or from a local system.
-
-### Usage
-```build_aarch64_wheel.py --key-name <YourPemKey> --use-docker --python 3.8 --branch <RCtag>```

.ci/aarch64_linux/aarch64_ci_build.sh

@@ -1,39 +0,0 @@
-#!/bin/bash
-set -eux -o pipefail
-
-GPU_ARCH_VERSION=${GPU_ARCH_VERSION:-}
-
-SCRIPTPATH="$( cd -- "$(dirname "$0")" >/dev/null 2>&1 ; pwd -P )"
-source $SCRIPTPATH/aarch64_ci_setup.sh
-
-tagged_version() {
-  GIT_DESCRIBE="git --git-dir /pytorch/.git describe --tags --match v[0-9]*.[0-9]*.[0-9]*"
-  if ${GIT_DESCRIBE} --exact >/dev/null; then
-    ${GIT_DESCRIBE}
-  else
-    return 1
-  fi
-}
-
-if tagged_version >/dev/null; then
-  export OVERRIDE_PACKAGE_VERSION="$(tagged_version | sed -e 's/^v//' -e 's/-.*$//')"
-fi
-
-###############################################################################
-# Run aarch64 builder python
-###############################################################################
-cd /
-# adding safe directory for git as the permissions will be
-# on the mounted pytorch repo
-git config --global --add safe.directory /pytorch
-pip install -r /pytorch/requirements.txt
-pip install auditwheel
-if [ "$DESIRED_CUDA" = "cpu" ]; then
-    echo "BASE_CUDA_VERSION is not set. Building cpu wheel."
-    #USE_PRIORITIZED_TEXT_FOR_LD for enable linker script optimization https://github.com/pytorch/pytorch/pull/121975/files
-    USE_PRIORITIZED_TEXT_FOR_LD=1 python /pytorch/.ci/aarch64_linux/aarch64_wheel_ci_build.py --enable-mkldnn
-else
-    echo "BASE_CUDA_VERSION is set to: $DESIRED_CUDA"
-    #USE_PRIORITIZED_TEXT_FOR_LD for enable linker script optimization https://github.com/pytorch/pytorch/pull/121975/files
-    USE_PRIORITIZED_TEXT_FOR_LD=1 python /pytorch/.ci/aarch64_linux/aarch64_wheel_ci_build.py --enable-mkldnn --enable-cuda
-fi

.ci/aarch64_linux/aarch64_ci_setup.sh

@@ -1,23 +0,0 @@
-#!/bin/bash
-set -eux -o pipefail
-
-# This script is used to prepare the Docker container for aarch64_ci_wheel_build.py python script
-# By creating symlinks from desired /opt/python to /usr/local/bin/
-
-NUMPY_VERSION=2.0.2
-PYGIT2_VERSION=1.15.1
-if [[ "$DESIRED_PYTHON"  == "3.13" ]]; then
-    NUMPY_VERSION=2.1.2
-    PYGIT2_VERSION=1.16.0
-fi
-
-SCRIPTPATH="$( cd "$(dirname "$0")" ; pwd -P )"
-source $SCRIPTPATH/../manywheel/set_desired_python.sh
-
-pip install -q numpy==${NUMPY_VERSION} pyyaml==6.0.2 scons==4.7.0 ninja==1.11.1 patchelf==0.17.2 pygit2==${PYGIT2_VERSION}
-
-for tool in python python3 pip pip3 ninja scons patchelf; do
-    ln -sf ${DESIRED_PYTHON_BIN_DIR}/${tool} /usr/local/bin;
-done
-
-python --version

.ci/aarch64_linux/aarch64_wheel_ci_build.py

@@ -1,230 +0,0 @@
-#!/usr/bin/env python3
-# encoding: UTF-8
-
-import os
-import shutil
-from subprocess import check_call, check_output
-from typing import List
-
-from pygit2 import Repository
-
-
-def list_dir(path: str) -> List[str]:
-    """'
-    Helper for getting paths for Python
-    """
-    return check_output(["ls", "-1", path]).decode().split("\n")
-
-
-def build_ArmComputeLibrary() -> None:
-    """
-    Using ArmComputeLibrary for aarch64 PyTorch
-    """
-    print("Building Arm Compute Library")
-    acl_build_flags = [
-        "debug=0",
-        "neon=1",
-        "opencl=0",
-        "os=linux",
-        "openmp=1",
-        "cppthreads=0",
-        "arch=armv8a",
-        "multi_isa=1",
-        "fixed_format_kernels=1",
-        "build=native",
-    ]
-    acl_install_dir = "/acl"
-    acl_checkout_dir = "ComputeLibrary"
-    os.makedirs(acl_install_dir)
-    check_call(
-        [
-            "git",
-            "clone",
-            "https://github.com/ARM-software/ComputeLibrary.git",
-            "-b",
-            "v24.09",
-            "--depth",
-            "1",
-            "--shallow-submodules",
-        ]
-    )
-
-    check_call(
-        ["scons", "Werror=1", "-j8", f"build_dir=/{acl_install_dir}/build"]
-        + acl_build_flags,
-        cwd=acl_checkout_dir,
-    )
-    for d in ["arm_compute", "include", "utils", "support", "src"]:
-        shutil.copytree(f"{acl_checkout_dir}/{d}", f"{acl_install_dir}/{d}")
-
-
-def update_wheel(wheel_path) -> None:
-    """
-    Update the cuda wheel libraries
-    """
-    folder = os.path.dirname(wheel_path)
-    wheelname = os.path.basename(wheel_path)
-    os.mkdir(f"{folder}/tmp")
-    os.system(f"unzip {wheel_path} -d {folder}/tmp")
-    libs_to_copy = [
-        "/usr/local/cuda/extras/CUPTI/lib64/libcupti.so.12",
-        "/usr/local/cuda/lib64/libcudnn.so.9",
-        "/usr/local/cuda/lib64/libcublas.so.12",
-        "/usr/local/cuda/lib64/libcublasLt.so.12",
-        "/usr/local/cuda/lib64/libcudart.so.12",
-        "/usr/local/cuda/lib64/libcufft.so.11",
-        "/usr/local/cuda/lib64/libcusparse.so.12",
-        "/usr/local/cuda/lib64/libcusparseLt.so.0",
-        "/usr/local/cuda/lib64/libcusolver.so.11",
-        "/usr/local/cuda/lib64/libcurand.so.10",
-        "/usr/local/cuda/lib64/libnvToolsExt.so.1",
-        "/usr/local/cuda/lib64/libnvJitLink.so.12",
-        "/usr/local/cuda/lib64/libnvrtc.so.12",
-        "/usr/local/cuda/lib64/libnvrtc-builtins.so.12.6",
-        "/usr/local/cuda/lib64/libcudnn_adv.so.9",
-        "/usr/local/cuda/lib64/libcudnn_cnn.so.9",
-        "/usr/local/cuda/lib64/libcudnn_graph.so.9",
-        "/usr/local/cuda/lib64/libcudnn_ops.so.9",
-        "/usr/local/cuda/lib64/libcudnn_engines_runtime_compiled.so.9",
-        "/usr/local/cuda/lib64/libcudnn_engines_precompiled.so.9",
-        "/usr/local/cuda/lib64/libcudnn_heuristic.so.9",
-        "/lib64/libgomp.so.1",
-        "/usr/lib64/libgfortran.so.5",
-        "/acl/build/libarm_compute.so",
-        "/acl/build/libarm_compute_graph.so",
-    ]
-    if enable_cuda:
-        libs_to_copy += [
-            "/usr/local/lib/libnvpl_lapack_lp64_gomp.so.0",
-            "/usr/local/lib/libnvpl_blas_lp64_gomp.so.0",
-            "/usr/local/lib/libnvpl_lapack_core.so.0",
-            "/usr/local/lib/libnvpl_blas_core.so.0",
-        ]
-    else:
-        libs_to_copy += [
-            "/opt/OpenBLAS/lib/libopenblas.so.0",
-        ]
-    # Copy libraries to unzipped_folder/a/lib
-    for lib_path in libs_to_copy:
-        lib_name = os.path.basename(lib_path)
-        shutil.copy2(lib_path, f"{folder}/tmp/torch/lib/{lib_name}")
-        os.system(
-            f"cd {folder}/tmp/torch/lib/; "
-            f"patchelf --set-rpath '$ORIGIN' --force-rpath {folder}/tmp/torch/lib/{lib_name}"
-        )
-    os.mkdir(f"{folder}/cuda_wheel")
-    os.system(f"cd {folder}/tmp/; zip -r {folder}/cuda_wheel/{wheelname} *")
-    shutil.move(
-        f"{folder}/cuda_wheel/{wheelname}",
-        f"{folder}/{wheelname}",
-        copy_function=shutil.copy2,
-    )
-    os.system(f"rm -rf {folder}/tmp/ {folder}/cuda_wheel/")
-
-
-def complete_wheel(folder: str) -> str:
-    """
-    Complete wheel build and put in artifact location
-    """
-    wheel_name = list_dir(f"/{folder}/dist")[0]
-
-    if "pytorch" in folder and not enable_cuda:
-        print("Repairing Wheel with AuditWheel")
-        check_call(["auditwheel", "repair", f"dist/{wheel_name}"], cwd=folder)
-        repaired_wheel_name = list_dir(f"/{folder}/wheelhouse")[0]
-
-        print(f"Moving {repaired_wheel_name} wheel to /{folder}/dist")
-        os.rename(
-            f"/{folder}/wheelhouse/{repaired_wheel_name}",
-            f"/{folder}/dist/{repaired_wheel_name}",
-        )
-    else:
-        repaired_wheel_name = wheel_name
-
-    print(f"Copying {repaired_wheel_name} to artifacts")
-    shutil.copy2(
-        f"/{folder}/dist/{repaired_wheel_name}", f"/artifacts/{repaired_wheel_name}"
-    )
-
-    return repaired_wheel_name
-
-
-def parse_arguments():
-    """
-    Parse inline arguments
-    """
-    from argparse import ArgumentParser
-
-    parser = ArgumentParser("AARCH64 wheels python CD")
-    parser.add_argument("--debug", action="store_true")
-    parser.add_argument("--build-only", action="store_true")
-    parser.add_argument("--test-only", type=str)
-    parser.add_argument("--enable-mkldnn", action="store_true")
-    parser.add_argument("--enable-cuda", action="store_true")
-    return parser.parse_args()
-
-
-if __name__ == "__main__":
-    """
-    Entry Point
-    """
-    args = parse_arguments()
-    enable_mkldnn = args.enable_mkldnn
-    enable_cuda = args.enable_cuda
-    repo = Repository("/pytorch")
-    branch = repo.head.name
-    if branch == "HEAD":
-        branch = "master"
-
-    print("Building PyTorch wheel")
-    build_vars = "MAX_JOBS=5 CMAKE_SHARED_LINKER_FLAGS=-Wl,-z,max-page-size=0x10000 "
-    os.system("cd /pytorch; python setup.py clean")
-
-    override_package_version = os.getenv("OVERRIDE_PACKAGE_VERSION")
-    if override_package_version is not None:
-        version = override_package_version
-        build_vars += (
-            f"BUILD_TEST=0 PYTORCH_BUILD_VERSION={version} PYTORCH_BUILD_NUMBER=1 "
-        )
-    elif branch in ["nightly", "master"]:
-        build_date = (
-            check_output(["git", "log", "--pretty=format:%cs", "-1"], cwd="/pytorch")
-            .decode()
-            .replace("-", "")
-        )
-        version = (
-            check_output(["cat", "version.txt"], cwd="/pytorch").decode().strip()[:-2]
-        )
-        if enable_cuda:
-            desired_cuda = os.getenv("DESIRED_CUDA")
-            build_vars += f"BUILD_TEST=0 PYTORCH_BUILD_VERSION={version}.dev{build_date}+{desired_cuda} PYTORCH_BUILD_NUMBER=1 "
-        else:
-            build_vars += f"BUILD_TEST=0 PYTORCH_BUILD_VERSION={version}.dev{build_date} PYTORCH_BUILD_NUMBER=1 "
-    elif branch.startswith(("v1.", "v2.")):
-        build_vars += f"BUILD_TEST=0 PYTORCH_BUILD_VERSION={branch[1:branch.find('-')]} PYTORCH_BUILD_NUMBER=1 "
-
-    if enable_mkldnn:
-        build_ArmComputeLibrary()
-        print("build pytorch with mkldnn+acl backend")
-        build_vars += (
-            "USE_MKLDNN=ON USE_MKLDNN_ACL=ON "
-            "ACL_ROOT_DIR=/acl "
-            "LD_LIBRARY_PATH=/pytorch/build/lib:/acl/build:$LD_LIBRARY_PATH "
-            "ACL_INCLUDE_DIR=/acl/build "
-            "ACL_LIBRARY=/acl/build "
-        )
-        if enable_cuda:
-            build_vars += "BLAS=NVPL "
-        else:
-            build_vars += "BLAS=OpenBLAS OpenBLAS_HOME=/OpenBLAS "
-    else:
-        print("build pytorch without mkldnn backend")
-
-    os.system(f"cd /pytorch; {build_vars} python3 setup.py bdist_wheel")
-    if enable_cuda:
-        print("Updating Cuda Dependency")
-        filename = os.listdir("/pytorch/dist/")
-        wheel_path = f"/pytorch/dist/{filename[0]}"
-        update_wheel(wheel_path)
-    pytorch_wheel_name = complete_wheel("/pytorch/")
-    print(f"Build Complete. Created {pytorch_wheel_name}..")

.ci/aarch64_linux/embed_library.py

@@ -1,87 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import shutil
-import sys
-from subprocess import check_call
-from tempfile import TemporaryDirectory
-
-from auditwheel.elfutils import elf_file_filter
-from auditwheel.lddtree import lddtree
-from auditwheel.patcher import Patchelf
-from auditwheel.repair import copylib
-from auditwheel.wheeltools import InWheelCtx
-
-
-def replace_tag(filename):
-    with open(filename) as f:
-        lines = f.read().split("\\n")
-    for i, line in enumerate(lines):
-        if not line.startswith("Tag: "):
-            continue
-        lines[i] = line.replace("-linux_", "-manylinux2014_")
-        print(f"Updated tag from {line} to {lines[i]}")
-
-    with open(filename, "w") as f:
-        f.write("\\n".join(lines))
-
-
-class AlignedPatchelf(Patchelf):
-    def set_soname(self, file_name: str, new_soname: str) -> None:
-        check_call(
-            ["patchelf", "--page-size", "65536", "--set-soname", new_soname, file_name]
-        )
-
-    def replace_needed(self, file_name: str, soname: str, new_soname: str) -> None:
-        check_call(
-            [
-                "patchelf",
-                "--page-size",
-                "65536",
-                "--replace-needed",
-                soname,
-                new_soname,
-                file_name,
-            ]
-        )
-
-
-def embed_library(whl_path, lib_soname, update_tag=False):
-    patcher = AlignedPatchelf()
-    out_dir = TemporaryDirectory()
-    whl_name = os.path.basename(whl_path)
-    tmp_whl_name = os.path.join(out_dir.name, whl_name)
-    with InWheelCtx(whl_path) as ctx:
-        torchlib_path = os.path.join(ctx._tmpdir.name, "torch", "lib")
-        ctx.out_wheel = tmp_whl_name
-        new_lib_path, new_lib_soname = None, None
-        for filename, _ in elf_file_filter(ctx.iter_files()):
-            if not filename.startswith("torch/lib"):
-                continue
-            libtree = lddtree(filename)
-            if lib_soname not in libtree["needed"]:
-                continue
-            lib_path = libtree["libs"][lib_soname]["path"]
-            if lib_path is None:
-                print(f"Can't embed {lib_soname} as it could not be found")
-                break
-            if lib_path.startswith(torchlib_path):
-                continue
-
-            if new_lib_path is None:
-                new_lib_soname, new_lib_path = copylib(lib_path, torchlib_path, patcher)
-            patcher.replace_needed(filename, lib_soname, new_lib_soname)
-            print(f"Replacing {lib_soname} with {new_lib_soname} for {filename}")
-        if update_tag:
-            # Add manylinux2014 tag
-            for filename in ctx.iter_files():
-                if os.path.basename(filename) != "WHEEL":
-                    continue
-                replace_tag(filename)
-    shutil.move(tmp_whl_name, whl_path)
-
-
-if __name__ == "__main__":
-    embed_library(
-        sys.argv[1], "libgomp.so.1", len(sys.argv) > 2 and sys.argv[2] == "--update-tag"
-    )

.ci/docker/aotriton_version.txt

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

.ci/docker/build.sh

@@ -179,21 +179,6 @@ case "$image" in
     TRITON=yes
     INDUCTOR_BENCHMARKS=yes
     ;;
-  pytorch-linux-focal-cuda12.4-cudnn9-py3.13-gcc9-inductor-benchmarks)
-    CUDA_VERSION=12.4.1
-    CUDNN_VERSION=9
-    ANACONDA_PYTHON_VERSION=3.13
-    GCC_VERSION=9
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    KATEX=yes
-    UCX_COMMIT=${_UCX_COMMIT}
-    UCC_COMMIT=${_UCC_COMMIT}
-    CONDA_CMAKE=yes
-    TRITON=yes
-    INDUCTOR_BENCHMARKS=yes
-    ;;
   pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9)
     CUDA_VERSION=11.8.0
     CUDNN_VERSION=9
@@ -280,6 +265,7 @@ case "$image" in
     SWIFTSHADER=yes
     CONDA_CMAKE=yes
     TRITON=yes
+    GRAPHVIZ=yes
     ;;
   pytorch-linux-focal-py3.9-gcc9)
     ANACONDA_PYTHON_VERSION=3.9
@@ -307,7 +293,7 @@ case "$image" in
     PROTOBUF=yes
     DB=yes
     VISION=yes
-    ROCM_VERSION=6.2.4
+    ROCM_VERSION=6.2
     NINJA_VERSION=1.9.0
     CONDA_CMAKE=yes
     TRITON=yes
@@ -323,17 +309,6 @@ case "$image" in
     CONDA_CMAKE=yes
     TRITON=yes
     ;;
-  pytorch-linux-jammy-xpu-2025.0-py3)
-    ANACONDA_PYTHON_VERSION=3.9
-    GCC_VERSION=11
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    XPU_VERSION=2025.0
-    NINJA_VERSION=1.9.0
-    CONDA_CMAKE=yes
-    TRITON=yes
-    ;;
     pytorch-linux-jammy-py3.9-gcc11-inductor-benchmarks)
     ANACONDA_PYTHON_VERSION=3.9
     GCC_VERSION=11
@@ -525,7 +500,7 @@ docker build \
        --build-arg "NINJA_VERSION=${NINJA_VERSION:-}" \
        --build-arg "KATEX=${KATEX:-}" \
        --build-arg "ROCM_VERSION=${ROCM_VERSION:-}" \
-       --build-arg "PYTORCH_ROCM_ARCH=${PYTORCH_ROCM_ARCH:-gfx90a}" \
+       --build-arg "PYTORCH_ROCM_ARCH=${PYTORCH_ROCM_ARCH:-gfx906;gfx90a}" \
        --build-arg "IMAGE_NAME=${IMAGE_NAME}" \
        --build-arg "UCX_COMMIT=${UCX_COMMIT}" \
        --build-arg "UCC_COMMIT=${UCC_COMMIT}" \

.ci/docker/ci_commit_pins/executorch.txt

@@ -1 +1 @@
-6f638937d64e3396793956d75ee3e14802022745
+91c382df0d2b2ef383d57998a61187cfefcb26e3

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

@@ -1 +1 @@
-e98b6fcb8df5b44eb0d0addb6767c573d37ba024
+91b14bf5593cf58a8541f3e6b9125600a867d4ef

.ci/docker/ci_commit_pins/triton.txt

@@ -1 +1 @@
-35c6c7c6284582b3f41c71c150e11b517acf074a
+cf34004b8a67d290a962da166f5aa2fc66751326

.ci/docker/common/install_base.sh

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

.ci/docker/common/install_conda.sh

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

.ci/docker/common/install_cuda.sh

@@ -3,7 +3,7 @@
 set -ex
 
 NCCL_VERSION=v2.21.5-1
-CUDNN_VERSION=9.5.1.17
+CUDNN_VERSION=9.1.0.70
 
 function install_cusparselt_040 {
     # cuSparseLt license: https://docs.nvidia.com/cuda/cusparselt/license.html
@@ -38,19 +38,7 @@ function install_cusparselt_062 {
     rm -rf tmp_cusparselt
 }
 
-function install_cusparselt_063 {
-    # cuSparseLt license: https://docs.nvidia.com/cuda/cusparselt/license.html
-    mkdir tmp_cusparselt && pushd tmp_cusparselt
-    wget -q https://developer.download.nvidia.com/compute/cusparselt/redist/libcusparse_lt/linux-x86_64/libcusparse_lt-linux-x86_64-0.6.3.2-archive.tar.xz
-    tar xf libcusparse_lt-linux-x86_64-0.6.3.2-archive.tar.xz
-    cp -a libcusparse_lt-linux-x86_64-0.6.3.2-archive/include/* /usr/local/cuda/include/
-    cp -a libcusparse_lt-linux-x86_64-0.6.3.2-archive/lib/* /usr/local/cuda/lib64/
-    popd
-    rm -rf tmp_cusparselt
-}
-
 function install_118 {
-    CUDNN_VERSION=9.1.0.70
     echo "Installing CUDA 11.8 and cuDNN ${CUDNN_VERSION} and NCCL ${NCCL_VERSION} and cuSparseLt-0.4.0"
     rm -rf /usr/local/cuda-11.8 /usr/local/cuda
     # install CUDA 11.8.0 in the same container
@@ -117,7 +105,6 @@ function install_121 {
 }
 
 function install_124 {
-  CUDNN_VERSION=9.1.0.70
   echo "Installing CUDA 12.4.1 and cuDNN ${CUDNN_VERSION} and NCCL ${NCCL_VERSION} and cuSparseLt-0.6.2"
   rm -rf /usr/local/cuda-12.4 /usr/local/cuda
   # install CUDA 12.4.1 in the same container
@@ -151,13 +138,13 @@ function install_124 {
 }
 
 function install_126 {
-  echo "Installing CUDA 12.6.3 and cuDNN ${CUDNN_VERSION} and NCCL ${NCCL_VERSION} and cuSparseLt-0.6.3"
+  echo "Installing CUDA 12.6.2 and cuDNN ${CUDNN_VERSION} and NCCL ${NCCL_VERSION} and cuSparseLt-0.6.2"
   rm -rf /usr/local/cuda-12.6 /usr/local/cuda
-  # install CUDA 12.6.3 in the same container
-  wget -q https://developer.download.nvidia.com/compute/cuda/12.6.3/local_installers/cuda_12.6.3_560.35.05_linux.run
-  chmod +x cuda_12.6.3_560.35.05_linux.run
-  ./cuda_12.6.3_560.35.05_linux.run --toolkit --silent
-  rm -f cuda_12.6.3_560.35.05_linux.run
+  # install CUDA 12.6.2 in the same container
+  wget -q https://developer.download.nvidia.com/compute/cuda/12.6.2/local_installers/cuda_12.6.2_560.35.03_linux.run
+  chmod +x cuda_12.6.2_560.35.03_linux.run
+  ./cuda_12.6.2_560.35.03_linux.run --toolkit --silent
+  rm -f cuda_12.6.2_560.35.03_linux.run
   rm -f /usr/local/cuda && ln -s /usr/local/cuda-12.6 /usr/local/cuda
 
   # cuDNN license: https://developer.nvidia.com/cudnn/license_agreement
@@ -178,7 +165,7 @@ function install_126 {
   cd ..
   rm -rf nccl
 
-  install_cusparselt_063
+  install_cusparselt_062
 
   ldconfig
 }

.ci/docker/common/install_cuda_aarch64.sh

@@ -4,7 +4,6 @@
 set -ex
 
 NCCL_VERSION=v2.21.5-1
-CUDNN_VERSION=9.5.1.17
 
 function install_cusparselt_062 {
     # cuSparseLt license: https://docs.nvidia.com/cuda/cusparselt/license.html
@@ -17,20 +16,8 @@ function install_cusparselt_062 {
     rm -rf tmp_cusparselt
 }
 
-function install_cusparselt_063 {
-    # cuSparseLt license: https://docs.nvidia.com/cuda/cusparselt/license.html
-    mkdir tmp_cusparselt && pushd tmp_cusparselt
-    wget -q https://developer.download.nvidia.com/compute/cusparselt/redist/libcusparse_lt/linux-sbsa/libcusparse_lt-linux-sbsa-0.6.3.2-archive.tar.xz
-    tar xf libcusparse_lt-linux-sbsa-0.6.3.2-archive.tar.xz
-    cp -a libcusparse_lt-linux-sbsa-0.6.3.2-archive/include/* /usr/local/cuda/include/
-    cp -a libcusparse_lt-linux-sbsa-0.6.3.2-archive/lib/* /usr/local/cuda/lib64/
-    popd
-    rm -rf tmp_cusparselt
-}
-
 function install_124 {
-  CUDNN_VERSION=9.1.0.70
-  echo "Installing CUDA 12.4.1 and cuDNN ${CUDNN_VERSION} and NCCL ${NCCL_VERSION} and cuSparseLt-0.6.2"
+  echo "Installing CUDA 12.4.1 and cuDNN 9.1 and NCCL ${NCCL_VERSION} and cuSparseLt-0.6.2"
   rm -rf /usr/local/cuda-12.4 /usr/local/cuda
   # install CUDA 12.4.1 in the same container
   wget -q https://developer.download.nvidia.com/compute/cuda/12.4.1/local_installers/cuda_12.4.1_550.54.15_linux_sbsa.run
@@ -41,10 +28,10 @@ function install_124 {
 
   # cuDNN license: https://developer.nvidia.com/cudnn/license_agreement
   mkdir tmp_cudnn && cd tmp_cudnn
-  wget -q https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-sbsa/cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive.tar.xz -O cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive.tar.xz
-  tar xf cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive.tar.xz
-  cp -a cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive/include/* /usr/local/cuda/include/
-  cp -a cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive/lib/* /usr/local/cuda/lib64/
+  wget -q https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-sbsa/cudnn-linux-sbsa-9.1.0.70_cuda12-archive.tar.xz -O cudnn-linux-sbsa-9.1.0.70_cuda12-archive.tar.xz
+  tar xf cudnn-linux-sbsa-9.1.0.70_cuda12-archive.tar.xz
+  cp -a cudnn-linux-sbsa-9.1.0.70_cuda12-archive/include/* /usr/local/cuda/include/
+  cp -a cudnn-linux-sbsa-9.1.0.70_cuda12-archive/lib/* /usr/local/cuda/lib64/
   cd ..
   rm -rf tmp_cudnn
 
@@ -87,87 +74,18 @@ function prune_124 {
   $NVPRUNE $GENCODE_CUDNN $CUDA_LIB_DIR/libcublasLt_static.a -o $CUDA_LIB_DIR/libcublasLt_static.a
 
   #####################################################################################
-  # CUDA 12.4 prune visual tools
+  # CUDA 12.1 prune visual tools
   #####################################################################################
   export CUDA_BASE="/usr/local/cuda-12.4/"
   rm -rf $CUDA_BASE/libnvvp $CUDA_BASE/nsightee_plugins $CUDA_BASE/nsight-compute-2024.1.0 $CUDA_BASE/nsight-systems-2023.4.4/
 }
 
-function install_126 {
-  echo "Installing CUDA 12.6.3 and cuDNN ${CUDNN_VERSION} and NCCL ${NCCL_VERSION} and cuSparseLt-0.6.3"
-  rm -rf /usr/local/cuda-12.6 /usr/local/cuda
-  # install CUDA 12.6.3 in the same container
-  wget -q https://developer.download.nvidia.com/compute/cuda/12.6.3/local_installers/cuda_12.6.3_560.35.05_linux_sbsa.run
-  chmod +x cuda_12.6.3_560.35.05_linux_sbsa.run
-  ./cuda_12.6.3_560.35.05_linux_sbsa.run --toolkit --silent
-  rm -f cuda_12.6.3_560.35.05_linux_sbsa.run
-  rm -f /usr/local/cuda && ln -s /usr/local/cuda-12.6 /usr/local/cuda
-
-  # cuDNN license: https://developer.nvidia.com/cudnn/license_agreement
-  mkdir tmp_cudnn && cd tmp_cudnn
-  wget -q https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-sbsa/cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive.tar.xz -O cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive.tar.xz
-  tar xf cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive.tar.xz
-  cp -a cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive/include/* /usr/local/cuda/include/
-  cp -a cudnn-linux-sbsa-${CUDNN_VERSION}_cuda12-archive/lib/* /usr/local/cuda/lib64/
-  cd ..
-  rm -rf tmp_cudnn
-
-  # NCCL license: https://docs.nvidia.com/deeplearning/nccl/#licenses
-  # Follow build: https://github.com/NVIDIA/nccl/tree/master?tab=readme-ov-file#build
-  git clone -b ${NCCL_VERSION} --depth 1 https://github.com/NVIDIA/nccl.git
-  cd nccl && make -j src.build
-  cp -a build/include/* /usr/local/cuda/include/
-  cp -a build/lib/* /usr/local/cuda/lib64/
-  cd ..
-  rm -rf nccl
-
-  install_cusparselt_063
-
-  ldconfig
-}
-
-function prune_126 {
-  echo "Pruning CUDA 12.6"
-  #####################################################################################
-  # CUDA 12.6 prune static libs
-  #####################################################################################
-  export NVPRUNE="/usr/local/cuda-12.6/bin/nvprune"
-  export CUDA_LIB_DIR="/usr/local/cuda-12.6/lib64"
-
-  export GENCODE="-gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=sm_75 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86 -gencode arch=compute_90,code=sm_90"
-  export GENCODE_CUDNN="-gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=sm_75 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86 -gencode arch=compute_90,code=sm_90"
-
-  if [[ -n "$OVERRIDE_GENCODE" ]]; then
-      export GENCODE=$OVERRIDE_GENCODE
-  fi
-  if [[ -n "$OVERRIDE_GENCODE_CUDNN" ]]; then
-      export GENCODE_CUDNN=$OVERRIDE_GENCODE_CUDNN
-  fi
-
-  # all CUDA libs except CuDNN and CuBLAS
-  ls $CUDA_LIB_DIR/ | grep "\.a" | grep -v "culibos" | grep -v "cudart" | grep -v "cudnn" | grep -v "cublas" | grep -v "metis"  \
-      | xargs -I {} bash -c \
-                "echo {} && $NVPRUNE $GENCODE $CUDA_LIB_DIR/{} -o $CUDA_LIB_DIR/{}"
-
-  # prune CuDNN and CuBLAS
-  $NVPRUNE $GENCODE_CUDNN $CUDA_LIB_DIR/libcublas_static.a -o $CUDA_LIB_DIR/libcublas_static.a
-  $NVPRUNE $GENCODE_CUDNN $CUDA_LIB_DIR/libcublasLt_static.a -o $CUDA_LIB_DIR/libcublasLt_static.a
-
-  #####################################################################################
-  # CUDA 12.6 prune visual tools
-  #####################################################################################
-  export CUDA_BASE="/usr/local/cuda-12.6/"
-  rm -rf $CUDA_BASE/libnvvp $CUDA_BASE/nsightee_plugins $CUDA_BASE/nsight-compute-2024.3.2 $CUDA_BASE/nsight-systems-2024.5.1/
-}
-
 # idiomatic parameter and option handling in sh
 while test $# -gt 0
 do
     case "$1" in
     12.4) install_124; prune_124
         ;;
-    12.6) install_126; prune_126
-        ;;
     *) echo "bad argument $1"; exit 1
         ;;
     esac

.ci/docker/common/install_cudnn.sh

@@ -4,9 +4,7 @@ if [[ -n "${CUDNN_VERSION}" ]]; then
     # cuDNN license: https://developer.nvidia.com/cudnn/license_agreement
     mkdir tmp_cudnn
     pushd tmp_cudnn
-    if [[ ${CUDA_VERSION:0:4} == "12.6" ]]; then
-        CUDNN_NAME="cudnn-linux-x86_64-9.5.1.17_cuda12-archive"
-    elif [[ ${CUDA_VERSION:0:2} == "12" ]]; then
+    if [[ ${CUDA_VERSION:0:2} == "12" ]]; then
         CUDNN_NAME="cudnn-linux-x86_64-9.1.0.70_cuda12-archive"
     elif [[ ${CUDA_VERSION:0:2} == "11" ]]; then
         CUDNN_NAME="cudnn-linux-x86_64-9.1.0.70_cuda11-archive"

.ci/docker/common/install_executorch.sh

@@ -36,19 +36,25 @@ install_conda_dependencies() {
 }
 
 install_pip_dependencies() {
-  pushd executorch
-  as_jenkins bash install_requirements.sh --pybind xnnpack
+  pushd executorch/.ci/docker
+  # Install PyTorch CPU build beforehand to avoid installing the much bigger CUDA
+  # binaries later, ExecuTorch only needs CPU
+  pip_install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+  # Install all Python dependencies
+  pip_install -r requirements-ci.txt
   popd
 }
 
 setup_executorch() {
   pushd executorch
+  # Setup swiftshader and Vulkan SDK which are required to build the Vulkan delegate
+  as_jenkins bash .ci/scripts/setup-vulkan-linux-deps.sh
 
   export PYTHON_EXECUTABLE=python
   export EXECUTORCH_BUILD_PYBIND=ON
   export CMAKE_ARGS="-DEXECUTORCH_BUILD_XNNPACK=ON -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON"
 
-  as_jenkins .ci/scripts/setup-linux.sh cmake || true
+  as_jenkins .ci/scripts/setup-linux.sh cmake
   popd
 }
 

.ci/docker/common/install_graphviz.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+set -ex
+
+source "$(dirname "${BASH_SOURCE[0]}")/common_utils.sh"
+
+if [ -n "${UBUNTU_VERSION}" ]; then
+    apt update
+    apt-get install -y graphviz
+elif [ -n "${CENTOS_VERSION}" ]; then
+    dnf update
+    dnf install -y graphviz
+else
+    echo "Unsupported Linux distribution"
+    exit 1
+fi

.ci/docker/common/install_inductor_benchmark_deps.sh

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

.ci/docker/common/install_magma.sh

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

.ci/docker/common/install_magma_conda.sh

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

.ci/docker/common/install_miopen.sh

@@ -16,7 +16,7 @@ case "$ID" in
   ubuntu)
     IS_UBUNTU=1
     ;;
-  centos|almalinux)
+  centos)
     IS_UBUNTU=0
     ;;
   *)
@@ -43,6 +43,12 @@ else
 fi
 ROCM_INT=$(($ROCM_VERSION_MAJOR * 10000 + $ROCM_VERSION_MINOR * 100 + $ROCM_VERSION_PATCH))
 
+# Install custom MIOpen + COMgr for ROCm >= 4.0.1
+if [[ $ROCM_INT -lt 40001 ]]; then
+    echo "ROCm version < 4.0.1; will not install custom MIOpen"
+    exit 0
+fi
+
 # Function to retry functions that sometimes timeout or have flaky failures
 retry () {
     $*  || (sleep 1 && $*) || (sleep 2 && $*) || (sleep 4 && $*) || (sleep 8 && $*)
@@ -60,27 +66,55 @@ else
     ROCM_INSTALL_PATH="/opt/rocm-${ROCM_VERSION}"
 fi
 
+# MIOPEN_USE_HIP_KERNELS is a Workaround for COMgr issues
 MIOPEN_CMAKE_COMMON_FLAGS="
 -DMIOPEN_USE_COMGR=ON
 -DMIOPEN_BUILD_DRIVER=OFF
 "
-if [[ $ROCM_INT -ge 60200 ]] && [[ $ROCM_INT -lt 60204 ]]; then
-    MIOPEN_BRANCH="release/rocm-rel-6.2-staging"
-else
-    echo "ROCm ${ROCM_VERSION} does not need any patches, do not build from source"
+# Pull MIOpen repo and set DMIOPEN_EMBED_DB based on ROCm version
+if [[ $ROCM_INT -ge 60300 ]]; then
+    echo "ROCm 6.3+ MIOpen does not need any patches, do not build from source"
     exit 0
+elif [[ $ROCM_INT -ge 60200 ]] && [[ $ROCM_INT -lt 60300 ]]; then
+    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
+elif [[ $ROCM_INT -ge 60000 ]] && [[ $ROCM_INT -lt 60100 ]]; then
+    echo "ROCm 6.0 MIOpen does not need any patches, do not build from source"
+    exit 0
+elif [[ $ROCM_INT -ge 50700 ]] && [[ $ROCM_INT -lt 60000 ]]; then
+    echo "ROCm 5.7 MIOpen does not need any patches, do not build from source"
+    exit 0
+elif [[ $ROCM_INT -ge 50600 ]] && [[ $ROCM_INT -lt 50700 ]]; then
+    MIOPEN_BRANCH="release/rocm-rel-5.6-staging"
+elif [[ $ROCM_INT -ge 50500 ]] && [[ $ROCM_INT -lt 50600 ]]; then
+    MIOPEN_BRANCH="release/rocm-rel-5.5-gfx11"
+elif [[ $ROCM_INT -ge 50400 ]] && [[ $ROCM_INT -lt 50500 ]]; then
+    MIOPEN_CMAKE_DB_FLAGS="-DMIOPEN_EMBED_DB=gfx900_56;gfx906_60;gfx90878;gfx90a6e;gfx1030_36 -DMIOPEN_USE_MLIR=Off"
+    MIOPEN_BRANCH="release/rocm-rel-5.4-staging"
+elif [[ $ROCM_INT -ge 50300 ]] && [[ $ROCM_INT -lt 50400 ]]; then
+    MIOPEN_CMAKE_DB_FLAGS="-DMIOPEN_EMBED_DB=gfx900_56;gfx906_60;gfx90878;gfx90a6e;gfx1030_36 -DMIOPEN_USE_MLIR=Off"
+    MIOPEN_BRANCH="release/rocm-rel-5.3-staging"
+elif [[ $ROCM_INT -ge 50200 ]] && [[ $ROCM_INT -lt 50300 ]]; then
+    MIOPEN_CMAKE_DB_FLAGS="-DMIOPEN_EMBED_DB=gfx900_56;gfx906_60;gfx90878;gfx90a6e;gfx1030_36 -DMIOPEN_USE_MLIR=Off"
+    MIOPEN_BRANCH="release/rocm-rel-5.2-staging"
+elif [[ $ROCM_INT -ge 50100 ]] && [[ $ROCM_INT -lt 50200 ]]; then
+    MIOPEN_CMAKE_DB_FLAGS="-DMIOPEN_EMBED_DB=gfx900_56;gfx906_60;gfx90878;gfx90a6e;gfx1030_36"
+    MIOPEN_BRANCH="release/rocm-rel-5.1-staging"
+elif [[ $ROCM_INT -ge 50000 ]] && [[ $ROCM_INT -lt 50100 ]]; then
+    MIOPEN_CMAKE_DB_FLAGS="-DMIOPEN_EMBED_DB=gfx900_56;gfx906_60;gfx90878;gfx90a6e;gfx1030_36"
+    MIOPEN_BRANCH="release/rocm-rel-5.0-staging"
+else
+    echo "Unhandled ROCM_VERSION ${ROCM_VERSION}"
+    exit 1
 fi
 
 
 if [[ ${IS_UBUNTU} == 1 ]]; then
   apt-get remove -y miopen-hip
 else
-  # Workaround since almalinux manylinux image already has this and cget doesn't like that
-  rm -rf /usr/local/lib/pkgconfig/sqlite3.pc
-
-  # Versioned package name needs regex match
-  # Use --noautoremove to prevent other rocm packages from being uninstalled
-  yum remove -y miopen-hip* --noautoremove
+  yum remove -y miopen-hip
 fi
 
 git clone https://github.com/ROCm/MIOpen -b ${MIOPEN_BRANCH}
@@ -88,7 +122,16 @@ 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
-sed -i '/composable_kernel/d' requirements.txt
+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
+    sed -i '/rocMLIR/d' requirements.txt
+elif [[ $ROCM_INT -ge 50200 ]] && [[ $ROCM_INT -lt 50400 ]]; then
+    sed -i '/llvm-project-mlir/d' requirements.txt
+fi
 ## MIOpen minimum requirements
 cmake -P install_deps.cmake --minimum
 
@@ -110,7 +153,7 @@ cd build
 PKG_CONFIG_PATH=/usr/local/lib/pkgconfig CXX=${ROCM_INSTALL_PATH}/llvm/bin/clang++ cmake .. \
     ${MIOPEN_CMAKE_COMMON_FLAGS} \
     ${MIOPEN_CMAKE_DB_FLAGS} \
-    -DCMAKE_PREFIX_PATH="${ROCM_INSTALL_PATH}"
+    -DCMAKE_PREFIX_PATH="${ROCM_INSTALL_PATH}/hip;${ROCM_INSTALL_PATH}"
 make MIOpen -j $(nproc)
 
 # Build MIOpen package

.ci/docker/common/install_onnx.sh

@@ -32,7 +32,7 @@ pip_install coloredlogs packaging
 
 pip_install onnxruntime==1.18.1
 pip_install onnx==1.16.2
-pip_install onnxscript==0.1.0.dev20241124 --no-deps
+pip_install onnxscript==0.1.0.dev20241009 --no-deps
 # required by onnxscript
 pip_install ml_dtypes
 

.ci/docker/common/install_openblas.sh

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

.ci/docker/common/install_rocm_drm.sh

@@ -12,7 +12,7 @@ case "$ID" in
     apt-get install -y libpciaccess-dev pkg-config
     apt-get clean
     ;;
-  centos|almalinux)
+  centos)
     yum install -y libpciaccess-devel pkgconfig
     ;;
   *)

.ci/docker/common/install_rocm_magma.sh

@@ -3,18 +3,6 @@
 
 set -ex
 
-# Magma build scripts need `python`
-ln -sf /usr/bin/python3 /usr/bin/python
-
-ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"')
-case "$ID" in
-  almalinux)
-    yum install -y gcc-gfortran
-    ;;
-  *)
-    echo "No preinstalls to build magma..."
-    ;;
-esac
 
 MKLROOT=${MKLROOT:-/opt/conda/envs/py_$ANACONDA_PYTHON_VERSION}
 

.ci/docker/common/install_xpu.sh

@@ -24,10 +24,10 @@ function install_ubuntu() {
         | tee /etc/apt/sources.list.d/intel-gpu-${VERSION_CODENAME}.list
     # To add the online network network package repository for the Intel Support Packages
     wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB \
-        | gpg --dearmor > /usr/share/keyrings/oneapi-archive-keyring.gpg.gpg
-    echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg.gpg] \
-        https://apt.repos.intel.com/${XPU_REPO_NAME} all main" \
-        | tee /etc/apt/sources.list.d/oneAPI.list
+        | gpg --dearmor > /usr/share/keyrings/intel-for-pytorch-gpu-dev-keyring.gpg
+    echo "deb [signed-by=/usr/share/keyrings/intel-for-pytorch-gpu-dev-keyring.gpg] \
+        https://apt.repos.intel.com/intel-for-pytorch-gpu-dev all main" \
+        | tee /etc/apt/sources.list.d/intel-for-pytorch-gpu-dev.list
 
     # Update the packages list and repository index
     apt-get update
@@ -47,7 +47,11 @@ function install_ubuntu() {
     # Development Packages
     apt-get install -y libigc-dev intel-igc-cm libigdfcl-dev libigfxcmrt-dev level-zero-dev
     # Install Intel Support Packages
-    apt-get install -y ${XPU_PACKAGES}
+    if [ -n "$XPU_VERSION" ]; then
+        apt-get install -y intel-for-pytorch-gpu-dev-${XPU_VERSION} intel-pti-dev-0.9
+    else
+        apt-get install -y intel-for-pytorch-gpu-dev-0.5 intel-pti-dev-0.9
+    fi
 
     # Cleanup
     apt-get autoclean && apt-get clean
@@ -57,13 +61,13 @@ function install_ubuntu() {
 function install_rhel() {
     . /etc/os-release
     if [[ "${ID}" == "rhel" ]]; then
-        if [[ ! " 8.8 8.9 9.0 9.2 9.3 " =~ " ${VERSION_ID} " ]]; then
+        if [[ ! " 8.6 8.8 8.9 9.0 9.2 9.3 " =~ " ${VERSION_ID} " ]]; then
             echo "RHEL version ${VERSION_ID} not supported"
             exit
         fi
     elif [[ "${ID}" == "almalinux" ]]; then
         # Workaround for almalinux8 which used by quay.io/pypa/manylinux_2_28_x86_64
-        VERSION_ID="8.8"
+        VERSION_ID="8.6"
     fi
 
     dnf install -y 'dnf-command(config-manager)'
@@ -71,18 +75,16 @@ function install_rhel() {
     dnf config-manager --add-repo \
         https://repositories.intel.com/gpu/rhel/${VERSION_ID}${XPU_DRIVER_VERSION}/unified/intel-gpu-${VERSION_ID}.repo
     # To add the online network network package repository for the Intel Support Packages
-    tee > /etc/yum.repos.d/oneAPI.repo << EOF
-[oneAPI]
+    tee > /etc/yum.repos.d/intel-for-pytorch-gpu-dev.repo << EOF
+[intel-for-pytorch-gpu-dev]
 name=Intel for Pytorch GPU dev repository
-baseurl=https://yum.repos.intel.com/${XPU_REPO_NAME}
+baseurl=https://yum.repos.intel.com/intel-for-pytorch-gpu-dev
 enabled=1
 gpgcheck=1
 repo_gpgcheck=1
 gpgkey=https://yum.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
 EOF
 
-    # Install Intel Support Packages
-    yum install -y ${XPU_PACKAGES}
     # The xpu-smi packages
     dnf install -y xpu-smi
     # Compute and Media Runtimes
@@ -97,6 +99,8 @@ EOF
     dnf install -y --refresh \
         intel-igc-opencl-devel level-zero-devel intel-gsc-devel libmetee-devel \
         level-zero-devel
+    # Install Intel Support Packages
+    yum install -y intel-for-pytorch-gpu-dev-0.5 intel-pti-dev-0.9
 
     # Cleanup
     dnf clean all
@@ -118,7 +122,7 @@ function install_sles() {
         https://repositories.intel.com/gpu/sles/${VERSION_SP}${XPU_DRIVER_VERSION}/unified/intel-gpu-${VERSION_SP}.repo
     rpm --import https://repositories.intel.com/gpu/intel-graphics.key
     # To add the online network network package repository for the Intel Support Packages
-    zypper addrepo https://yum.repos.intel.com/${XPU_REPO_NAME} oneAPI
+    zypper addrepo https://yum.repos.intel.com/intel-for-pytorch-gpu-dev intel-for-pytorch-gpu-dev
     rpm --import https://yum.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
 
     # The xpu-smi packages
@@ -130,7 +134,7 @@ function install_sles() {
     zypper install -y libigdfcl-devel intel-igc-cm libigfxcmrt-devel level-zero-devel
 
     # Install Intel Support Packages
-    zypper install -y ${XPU_PACKAGES}
+    zypper install -y intel-for-pytorch-gpu-dev-0.5 intel-pti-dev-0.9
 
 }
 
@@ -141,13 +145,6 @@ if [[ "${XPU_DRIVER_TYPE,,}" == "rolling" ]]; then
     XPU_DRIVER_VERSION=""
 fi
 
-XPU_REPO_NAME="intel-for-pytorch-gpu-dev"
-XPU_PACKAGES="intel-for-pytorch-gpu-dev-0.5 intel-pti-dev-0.9"
-if [[ "$XPU_VERSION" == "2025.0" ]]; then
-    XPU_REPO_NAME="oneapi"
-    XPU_PACKAGES="intel-deep-learning-essentials-2025.0"
-fi
-
 # The installation depends on the base OS
 ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"')
 case "$ID" in

.ci/docker/conda/Dockerfile

@@ -1,39 +1,47 @@
-ARG CUDA_VERSION=12.4
+ARG CUDA_VERSION=10.2
 ARG BASE_TARGET=cuda${CUDA_VERSION}
-FROM amd64/almalinux:8 as base
+FROM centos:7 as base
 
 ENV LC_ALL en_US.UTF-8
 ENV LANG en_US.UTF-8
 ENV LANGUAGE en_US.UTF-8
 
-ARG DEVTOOLSET_VERSION=11
-
-ENV LC_ALL en_US.UTF-8
-ENV LANG en_US.UTF-8
-ENV LANGUAGE en_US.UTF-8
-
-RUN yum -y update
-RUN yum -y install epel-release
-RUN yum install -y sudo wget curl perl util-linux xz bzip2 git patch which perl zlib-devel openssl-devel yum-utils autoconf automake make gcc-toolset-${DEVTOOLSET_VERSION}-toolchain
+ARG DEVTOOLSET_VERSION=9
+RUN sed -i s/mirror.centos.org/vault.centos.org/g /etc/yum.repos.d/*.repo
+RUN sed -i s/^#.*baseurl=http/baseurl=http/g /etc/yum.repos.d/*.repo
+RUN sed -i s/^mirrorlist=http/#mirrorlist=http/g /etc/yum.repos.d/*.repo
+RUN yum update -y
+RUN yum install -y wget curl perl util-linux xz bzip2 git patch which unzip
 # Just add everything as a safe.directory for git since these will be used in multiple places with git
 RUN git config --global --add safe.directory '*'
-ENV PATH=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/bin:$PATH
+RUN yum install -y yum-utils centos-release-scl
+RUN yum-config-manager --enable rhel-server-rhscl-7-rpms
+RUN sed -i s/mirror.centos.org/vault.centos.org/g /etc/yum.repos.d/*.repo
+RUN sed -i s/^#.*baseurl=http/baseurl=http/g /etc/yum.repos.d/*.repo
+RUN sed -i s/^mirrorlist=http/#mirrorlist=http/g /etc/yum.repos.d/*.repo
+RUN yum install -y devtoolset-${DEVTOOLSET_VERSION}-gcc devtoolset-${DEVTOOLSET_VERSION}-gcc-c++ devtoolset-${DEVTOOLSET_VERSION}-gcc-gfortran devtoolset-${DEVTOOLSET_VERSION}-binutils
+# EPEL for cmake
+RUN yum --enablerepo=extras install -y epel-release
 
-# cmake-3.18.4 from pip
-RUN yum install -y python3-pip && \
-    python3 -mpip install cmake==3.18.4 && \
-    ln -s /usr/local/bin/cmake /usr/bin/cmake3
+# cmake
+RUN yum install -y cmake3 && \
+    ln -s /usr/bin/cmake3 /usr/bin/cmake
+ENV PATH=/opt/rh/devtoolset-${DEVTOOLSET_VERSION}/root/usr/bin:$PATH
+ENV LD_LIBRARY_PATH=/opt/rh/devtoolset-${DEVTOOLSET_VERSION}/root/usr/lib64:/opt/rh/devtoolset-${DEVTOOLSET_VERSION}/root/usr/lib:$LD_LIBRARY_PATH
+
+RUN yum install -y autoconf aclocal automake make sudo
 RUN rm -rf /usr/local/cuda-*
 
-FROM base as openssl
-ADD ./common/install_openssl.sh install_openssl.sh
-RUN bash ./install_openssl.sh && rm install_openssl.sh
-
 FROM base as patchelf
 # Install patchelf
 ADD ./common/install_patchelf.sh install_patchelf.sh
 RUN bash ./install_patchelf.sh && rm install_patchelf.sh && cp $(which patchelf) /patchelf
 
+FROM base as openssl
+# Install openssl
+ADD ./common/install_openssl.sh install_openssl.sh
+RUN bash ./install_openssl.sh && rm install_openssl.sh
+
 FROM base as conda
 # Install Anaconda
 ADD ./common/install_conda_docker.sh install_conda.sh
@@ -41,7 +49,7 @@ RUN bash ./install_conda.sh && rm install_conda.sh
 
 # Install CUDA
 FROM base as cuda
-ARG CUDA_VERSION=12.4
+ARG CUDA_VERSION=10.2
 RUN rm -rf /usr/local/cuda-*
 ADD ./common/install_cuda.sh install_cuda.sh
 ENV CUDA_HOME=/usr/local/cuda-${CUDA_VERSION}
@@ -88,8 +96,7 @@ COPY ./common/install_jni.sh install_jni.sh
 COPY ./java/jni.h jni.h
 RUN bash ./install_jni.sh && rm install_jni.sh
 
-ENV PATH /opt/conda/bin:$PATH
-ENV LD_LIBRARY_PATH=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib64:/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib:$LD_LIBRARY_PATH
+ENV  PATH /opt/conda/bin:$PATH
 COPY --from=mnist  /usr/local/mnist /usr/local/mnist
 RUN rm -rf /usr/local/cuda
 RUN chmod o+rw /usr/local

.ci/docker/conda/build.sh

@@ -48,10 +48,10 @@ esac
     --progress plain \
     --build-arg "BASE_TARGET=${BASE_TARGET}" \
     --build-arg "CUDA_VERSION=${CUDA_VERSION}" \
-    --build-arg "DEVTOOLSET_VERSION=11" \
+    --build-arg "DEVTOOLSET_VERSION=9" \
     -t ${DOCKER_IMAGE_NAME} \
     $@ \
-    -f "${TOPDIR}/.ci/docker/almalinux/Dockerfile" \
+    -f "${TOPDIR}/.ci/docker/conda/Dockerfile" \
     ${TOPDIR}/.ci/docker/
 )
 

.ci/docker/libtorch/build.sh

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

.ci/docker/linter-cuda/Dockerfile

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

.ci/docker/manywheel/Dockerfile

@@ -144,10 +144,6 @@ COPY --from=libpng             /usr/local/lib/pkgconfig              /usr/local/
 FROM common as cpu_final
 ARG BASE_CUDA_VERSION=10.1
 ARG DEVTOOLSET_VERSION=9
-# Install Anaconda
-ADD ./common/install_conda_docker.sh install_conda.sh
-RUN bash ./install_conda.sh && rm install_conda.sh
-ENV PATH /opt/conda/bin:$PATH
 RUN sed -i s/mirror.centos.org/vault.centos.org/g /etc/yum.repos.d/*.repo
 RUN sed -i s/^#.*baseurl=http/baseurl=http/g /etc/yum.repos.d/*.repo
 RUN sed -i s/^mirrorlist=http/#mirrorlist=http/g /etc/yum.repos.d/*.repo

.ci/docker/manywheel/Dockerfile_2_28

@@ -1,4 +1,5 @@
 # syntax = docker/dockerfile:experimental
+ARG ROCM_VERSION=3.7
 ARG BASE_CUDA_VERSION=11.8
 ARG GPU_IMAGE=amd64/almalinux:8
 FROM quay.io/pypa/manylinux_2_28_x86_64 as base
@@ -116,49 +117,30 @@ COPY --from=jni                /usr/local/include/jni.h              /usr/local/
 FROM common as cpu_final
 ARG BASE_CUDA_VERSION=11.8
 ARG DEVTOOLSET_VERSION=11
-# Install Anaconda
-ADD ./common/install_conda_docker.sh install_conda.sh
-RUN bash ./install_conda.sh && rm install_conda.sh
-ENV PATH /opt/conda/bin:$PATH
 # Ensure the expected devtoolset is used
 ENV PATH=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/bin:$PATH
 ENV LD_LIBRARY_PATH=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib64:/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib:$LD_LIBRARY_PATH
-# Install setuptools and wheel for python 3.12/3.13
-RUN for cpython_version in "cp312-cp312" "cp313-cp313" "cp313-cp313t"; do \
-    /opt/python/${cpython_version}/bin/python -m pip install setuptools wheel; \
-    done;
 
-
-# cmake-3.18.4 from pip; force in case cmake3 already exists
+# cmake-3.18.4 from pip
 RUN yum install -y python3-pip && \
     python3 -mpip install cmake==3.18.4 && \
-    ln -sf /usr/local/bin/cmake /usr/bin/cmake3
+    ln -s /usr/local/bin/cmake /usr/bin/cmake3
 
 FROM cpu_final as cuda_final
 RUN rm -rf /usr/local/cuda-${BASE_CUDA_VERSION}
 COPY --from=cuda     /usr/local/cuda-${BASE_CUDA_VERSION}  /usr/local/cuda-${BASE_CUDA_VERSION}
 COPY --from=magma    /usr/local/cuda-${BASE_CUDA_VERSION}  /usr/local/cuda-${BASE_CUDA_VERSION}
-RUN ln -sf /usr/local/cuda-${BASE_CUDA_VERSION} /usr/local/cuda
-ENV PATH=/usr/local/cuda/bin:$PATH
 
-FROM cpu_final as rocm_final
-ARG ROCM_VERSION=6.0
-ARG PYTORCH_ROCM_ARCH
-ENV PYTORCH_ROCM_ARCH ${PYTORCH_ROCM_ARCH}
-ARG DEVTOOLSET_VERSION=11
-ENV LDFLAGS="-Wl,-rpath=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib64 -Wl,-rpath=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib"
-# Somewhere in ROCm stack, we still use non-existing /opt/rocm/hip path,
-# below workaround helps avoid error
-ENV ROCM_PATH /opt/rocm
-# cmake-3.28.4 from pip to get enable_language(HIP)
-# and avoid 3.21.0 cmake+ninja issues with ninja inserting "-Wl,--no-as-needed" in LINK_FLAGS for static linker
-RUN python3 -m pip install --upgrade pip && \
-    python3 -mpip install cmake==3.28.4
-ADD ./common/install_rocm_drm.sh install_rocm_drm.sh
-RUN bash ./install_rocm_drm.sh && rm install_rocm_drm.sh
-ENV MKLROOT /opt/intel
-ADD ./common/install_rocm_magma.sh install_rocm_magma.sh
-RUN bash ./install_rocm_magma.sh && rm install_rocm_magma.sh
+FROM common as rocm_final
+ARG ROCM_VERSION=3.7
+# Install ROCm
+ADD ./common/install_rocm.sh install_rocm.sh
+RUN bash ./install_rocm.sh ${ROCM_VERSION} && rm install_rocm.sh
+# cmake is already installed inside the rocm base image, but both 2 and 3 exist
+# cmake3 is needed for the later MIOpen custom build, so that step is last.
+RUN yum install -y cmake3 && \
+    rm -f /usr/bin/cmake && \
+    ln -s /usr/bin/cmake3 /usr/bin/cmake
 ADD ./common/install_miopen.sh install_miopen.sh
 RUN bash ./install_miopen.sh ${ROCM_VERSION} && rm install_miopen.sh
 
@@ -168,7 +150,8 @@ ENV XPU_DRIVER_TYPE ROLLING
 # cmake-3.28.4 from pip
 RUN python3 -m pip install --upgrade pip && \
     python3 -mpip install cmake==3.28.4
+# Install setuptools and wheel for python 3.13
+RUN /opt/python/cp313-cp313/bin/python -m pip install setuptools wheel
 ADD ./common/install_xpu.sh install_xpu.sh
-ENV XPU_VERSION 2025.0
 RUN bash ./install_xpu.sh && rm install_xpu.sh
 RUN pushd /opt/_internal && tar -xJf static-libs-for-embedding-only.tar.xz && popd

.ci/docker/manywheel/Dockerfile_2_28_aarch64

@@ -48,11 +48,6 @@ ENV LD_LIBRARY_PATH=/opt/rh/gcc-toolset-${GCCTOOLSET_VERSION}/root/usr/lib64:/op
 # For more details see https://github.com/pytorch/pytorch/issues/78659#issuecomment-1144107327
 RUN git config --global --add safe.directory "*"
 
-FROM base as openblas
-# Install openblas
-ADD ./common/install_openblas.sh install_openblas.sh
-RUN bash ./install_openblas.sh && rm install_openblas.sh
-
 FROM base as final
 
 # remove unncessary python versions
@@ -60,5 +55,3 @@ RUN rm -rf /opt/python/cp26-cp26m /opt/_internal/cpython-2.6.9-ucs2
 RUN rm -rf /opt/python/cp26-cp26mu /opt/_internal/cpython-2.6.9-ucs4
 RUN rm -rf /opt/python/cp33-cp33m /opt/_internal/cpython-3.3.6
 RUN rm -rf /opt/python/cp34-cp34m /opt/_internal/cpython-3.4.6
-COPY --from=openblas     /opt/OpenBLAS/  /opt/OpenBLAS/
-ENV LD_LIBRARY_PATH=/opt/OpenBLAS/lib:$LD_LIBRARY_PATH

.ci/docker/manywheel/Dockerfile_aarch64

@@ -61,7 +61,7 @@ RUN git config --global --add safe.directory "*"
 # NOTE: Need a better way to get this library as Ubuntu's package can be removed by the vender, or changed
 ###############################################################################
 RUN cd ~/ \
-  && curl -L -o ~/libgfortran-10-dev.deb http://ports.ubuntu.com/ubuntu-ports/pool/universe/g/gcc-10/libgfortran-10-dev_10.5.0-4ubuntu2_arm64.deb \
+  && curl -L -o ~/libgfortran-10-dev.deb http://ports.ubuntu.com/ubuntu-ports/pool/universe/g/gcc-10/libgfortran-10-dev_10.5.0-1ubuntu1_arm64.deb \
   && ar x ~/libgfortran-10-dev.deb \
   && tar --use-compress-program=unzstd -xvf data.tar.zst -C ~/ \
   && cp -f ~/usr/lib/gcc/aarch64-linux-gnu/10/libgfortran.a /opt/rh/devtoolset-10/root/usr/lib/gcc/aarch64-redhat-linux/10/

.ci/docker/manywheel/Dockerfile_s390x

@@ -1,20 +1,17 @@
-FROM quay.io/pypa/manylinux_2_28_s390x as base
+FROM --platform=linux/s390x docker.io/ubuntu:24.04 as base
 
 # Language variables
 ENV LC_ALL=C.UTF-8
 ENV LANG=C.UTF-8
 ENV LANGUAGE=C.UTF-8
 
-ARG DEVTOOLSET_VERSION=13
 # Installed needed OS packages. This is to support all
 # the binary builds (torch, vision, audio, text, data)
-RUN yum -y install epel-release
-RUN yum -y update
-RUN yum install -y \
-  sudo \
+RUN apt update ; apt upgrade -y
+RUN apt install -y \
+  build-essential \
   autoconf \
   automake \
-  bison \
   bzip2 \
   curl \
   diffutils \
@@ -27,40 +24,19 @@ RUN yum install -y \
   util-linux \
   wget \
   which \
-  xz \
-  yasm \
+  xz-utils \
   less \
   zstd \
-  libgomp \
-  gcc-toolset-${DEVTOOLSET_VERSION}-gcc \
-  gcc-toolset-${DEVTOOLSET_VERSION}-gcc-c++ \
-  gcc-toolset-${DEVTOOLSET_VERSION}-binutils \
-  gcc-toolset-${DEVTOOLSET_VERSION}-gcc-gfortran \
   cmake \
-  rust \
-  cargo \
-  llvm-devel \
-  libzstd-devel \
-  python3.12-devel \
-  python3.12-setuptools \
-  python3.12-pip \
-  python3-virtualenv \
-  python3.12-pyyaml \
-  python3.12-numpy \
-  python3.12-wheel \
-  python3.12-cryptography \
-  blas-devel \
-  openblas-devel \
-  lapack-devel \
-  atlas-devel \
-  libjpeg-devel \
-  libxslt-devel \
-  libxml2-devel \
-  openssl-devel \
-  valgrind
-
-ENV PATH=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/bin:$PATH
-ENV LD_LIBRARY_PATH=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib64:/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib:$LD_LIBRARY_PATH
+  python3 \
+  python3-dev \
+  python3-setuptools \
+  python3-yaml \
+  python3-typing-extensions \
+  libblas-dev \
+  libopenblas-dev \
+  liblapack-dev \
+  libatlas-base-dev
 
 # git236+ would refuse to run git commands in repos owned by other users
 # Which causes version check to fail, as pytorch repo is bind-mounted into the image
@@ -68,8 +44,14 @@ ENV LD_LIBRARY_PATH=/opt/rh/gcc-toolset-${DEVTOOLSET_VERSION}/root/usr/lib64:/op
 # For more details see https://github.com/pytorch/pytorch/issues/78659#issuecomment-1144107327
 RUN git config --global --add safe.directory "*"
 
-# installed python doesn't have development parts. Rebuild it from scratch
-RUN /bin/rm -rf /opt/_internal /opt/python /usr/local/*/*
+FROM base as openssl
+# Install openssl (this must precede `build python` step)
+# (In order to have a proper SSL module, Python is compiled
+# against a recent openssl [see env vars above], which is linked
+# statically. We delete openssl afterwards.)
+ADD ./common/install_openssl.sh install_openssl.sh
+RUN bash ./install_openssl.sh && rm install_openssl.sh
+ENV SSL_CERT_FILE=/opt/_internal/certs.pem
 
 # EPEL for cmake
 FROM base as patchelf
@@ -82,43 +64,10 @@ FROM patchelf as python
 # build python
 COPY manywheel/build_scripts /build_scripts
 ADD ./common/install_cpython.sh /build_scripts/install_cpython.sh
-ENV SSL_CERT_FILE=
 RUN bash build_scripts/build.sh && rm -r build_scripts
 
-FROM base as final
+FROM openssl as final
 COPY --from=python             /opt/python                           /opt/python
 COPY --from=python             /opt/_internal                        /opt/_internal
-COPY --from=python             /opt/python/cp39-cp39/bin/auditwheel  /usr/local/bin/auditwheel
+COPY --from=python             /opt/python/cp39-cp39/bin/auditwheel /usr/local/bin/auditwheel
 COPY --from=patchelf           /usr/local/bin/patchelf               /usr/local/bin/patchelf
-
-RUN alternatives --set python /usr/bin/python3.12
-RUN alternatives --set python3 /usr/bin/python3.12
-
-RUN pip-3.12 install typing_extensions
-
-ENTRYPOINT []
-CMD ["/bin/bash"]
-
-# install test dependencies:
-# - grpcio requires system openssl, bundled crypto fails to build
-# - ml_dtypes 0.4.0 requires some fixes provided in later commits to build
-RUN dnf install -y \
-  protobuf-devel \
-  protobuf-c-devel \
-  protobuf-lite-devel \
-  wget \
-  patch
-
-RUN env GRPC_PYTHON_BUILD_SYSTEM_OPENSSL=True pip3 install grpcio==1.65.4
-RUN cd ~ && \
-  git clone https://github.com/jax-ml/ml_dtypes && \
-  cd ml_dtypes && \
-  git checkout v0.4.0 && \
-  git submodule update --init --recursive && \
-  wget https://github.com/jax-ml/ml_dtypes/commit/b969f76914d6b30676721bc92bf0f6021a0d1321.patch && \
-  wget https://github.com/jax-ml/ml_dtypes/commit/d4e6d035ecda073eab8bcf60f4eef572ee7087e6.patch && \
-  patch -p1 < b969f76914d6b30676721bc92bf0f6021a0d1321.patch && \
-  patch -p1 < d4e6d035ecda073eab8bcf60f4eef572ee7087e6.patch && \
-  python3 setup.py bdist_wheel && \
-  pip3 install dist/*.whl && \
-  rm -rf ml_dtypes

.ci/docker/manywheel/build.sh

@@ -61,7 +61,7 @@ case ${GPU_ARCH_TYPE} in
     cpu-s390x)
         TARGET=final
         DOCKER_TAG=cpu-s390x
-        GPU_IMAGE=s390x/almalinux:8
+        GPU_IMAGE=redhat/ubi9
         DOCKER_GPU_BUILD_ARG=""
         MANY_LINUX_VERSION="s390x"
         ;;
@@ -87,18 +87,22 @@ case ${GPU_ARCH_TYPE} in
         MANY_LINUX_VERSION="aarch64"
         DOCKERFILE_SUFFIX="_cuda_aarch64"
         ;;
-    rocm|rocm-manylinux_2_28)
+    rocm)
         TARGET=rocm_final
         DOCKER_TAG=rocm${GPU_ARCH_VERSION}
         GPU_IMAGE=rocm/dev-centos-7:${GPU_ARCH_VERSION}-complete
-        DEVTOOLSET_VERSION="9"
-        if [ ${GPU_ARCH_TYPE} == "rocm-manylinux_2_28" ]; then
-            MANY_LINUX_VERSION="2_28"
-            DEVTOOLSET_VERSION="11"
-            GPU_IMAGE=rocm/dev-almalinux-8:${GPU_ARCH_VERSION}-complete
+        PYTORCH_ROCM_ARCH="gfx900;gfx906;gfx908;gfx90a;gfx1030;gfx1100"
+        ROCM_REGEX="([0-9]+)\.([0-9]+)[\.]?([0-9]*)"
+        if [[ $GPU_ARCH_VERSION =~ $ROCM_REGEX ]]; then
+            ROCM_VERSION_INT=$((${BASH_REMATCH[1]}*10000 + ${BASH_REMATCH[2]}*100 + ${BASH_REMATCH[3]:-0}))
+        else
+            echo "ERROR: rocm regex failed"
+            exit 1
         fi
-        PYTORCH_ROCM_ARCH="gfx900;gfx906;gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101"
-        DOCKER_GPU_BUILD_ARG="--build-arg ROCM_VERSION=${GPU_ARCH_VERSION} --build-arg PYTORCH_ROCM_ARCH=${PYTORCH_ROCM_ARCH} --build-arg DEVTOOLSET_VERSION=${DEVTOOLSET_VERSION}"
+        if [[ $ROCM_VERSION_INT -ge 60000 ]]; then
+            PYTORCH_ROCM_ARCH+=";gfx942"
+        fi
+        DOCKER_GPU_BUILD_ARG="--build-arg ROCM_VERSION=${GPU_ARCH_VERSION} --build-arg PYTORCH_ROCM_ARCH=${PYTORCH_ROCM_ARCH} --build-arg DEVTOOLSET_VERSION=9"
         ;;
     xpu)
         TARGET=xpu_final
@@ -121,13 +125,11 @@ fi
 (
     set -x
 
-    if [ "$(uname -m)" != "s390x" ]; then
-        # TODO: Remove LimitNOFILE=1048576 patch once https://github.com/pytorch/test-infra/issues/5712
-        # is resolved. This patch is required in order to fix timing out of Docker build on Amazon Linux 2023.
-        sudo sed -i s/LimitNOFILE=infinity/LimitNOFILE=1048576/ /usr/lib/systemd/system/docker.service
-        sudo systemctl daemon-reload
-        sudo systemctl restart docker
-    fi
+    # TODO: Remove LimitNOFILE=1048576 patch once https://github.com/pytorch/test-infra/issues/5712
+    # is resolved. This patch is required in order to fix timing out of Docker build on Amazon Linux 2023.
+    sudo sed -i s/LimitNOFILE=infinity/LimitNOFILE=1048576/ /usr/lib/systemd/system/docker.service
+    sudo systemctl daemon-reload
+    sudo systemctl restart docker
 
     DOCKER_BUILDKIT=1 docker build  \
         ${DOCKER_GPU_BUILD_ARG} \

.ci/docker/manywheel/build_scripts/build.sh

@@ -16,27 +16,37 @@ CURL_HASH=cf34fe0b07b800f1c01a499a6e8b2af548f6d0e044dca4a29d88a4bee146d131
 AUTOCONF_ROOT=autoconf-2.69
 AUTOCONF_HASH=954bd69b391edc12d6a4a51a2dd1476543da5c6bbf05a95b59dc0dd6fd4c2969
 
-# Dependencies for compiling Python that we want to remove from
-# the final image after compiling Python
-PYTHON_COMPILE_DEPS="zlib-devel bzip2-devel ncurses-devel sqlite-devel readline-devel tk-devel gdbm-devel libpcap-devel xz-devel libffi-devel"
-
-if [ "$(uname -m)" != "s390x" ] ; then
-    PYTHON_COMPILE_DEPS="${PYTHON_COMPILE_DEPS} db4-devel"
-else
-    PYTHON_COMPILE_DEPS="${PYTHON_COMPILE_DEPS} libdb-devel"
-fi
-
-# Libraries that are allowed as part of the manylinux1 profile
-MANYLINUX1_DEPS="glibc-devel libstdc++-devel glib2-devel libX11-devel libXext-devel libXrender-devel  mesa-libGL-devel libICE-devel libSM-devel ncurses-devel"
-
 # Get build utilities
 MY_DIR=$(dirname "${BASH_SOURCE[0]}")
 source $MY_DIR/build_utils.sh
 
-# Development tools and libraries
-yum -y install bzip2 make git patch unzip bison yasm diffutils \
-    automake which file \
-    ${PYTHON_COMPILE_DEPS}
+if [ "$(uname -m)" != "s390x" ] ; then
+    # Dependencies for compiling Python that we want to remove from
+    # the final image after compiling Python
+    PYTHON_COMPILE_DEPS="zlib-devel bzip2-devel ncurses-devel sqlite-devel readline-devel tk-devel gdbm-devel db4-devel libpcap-devel xz-devel libffi-devel"
+
+    # Libraries that are allowed as part of the manylinux1 profile
+    MANYLINUX1_DEPS="glibc-devel libstdc++-devel glib2-devel libX11-devel libXext-devel libXrender-devel  mesa-libGL-devel libICE-devel libSM-devel ncurses-devel"
+
+    # Development tools and libraries
+    yum -y install bzip2 make git patch unzip bison yasm diffutils \
+        automake which file cmake28 \
+        kernel-devel-`uname -r` \
+        ${PYTHON_COMPILE_DEPS}
+else
+    # Dependencies for compiling Python that we want to remove from
+    # the final image after compiling Python
+    PYTHON_COMPILE_DEPS="zlib1g-dev libbz2-dev libncurses-dev libsqlite3-dev libdb-dev libpcap-dev liblzma-dev libffi-dev"
+
+    # Libraries that are allowed as part of the manylinux1 profile
+    MANYLINUX1_DEPS="libglib2.0-dev libX11-dev libncurses-dev"
+
+    # Development tools and libraries
+    apt install -y bzip2 make git patch unzip diffutils \
+        automake which file cmake \
+        linux-headers-virtual \
+        ${PYTHON_COMPILE_DEPS}
+fi
 
 # Install newest autoconf
 build_autoconf $AUTOCONF_ROOT $AUTOCONF_HASH
@@ -82,13 +92,16 @@ ln -s $PY39_BIN/auditwheel /usr/local/bin/auditwheel
 
 # Clean up development headers and other unnecessary stuff for
 # final image
-yum -y erase wireless-tools gtk2 libX11 hicolor-icon-theme \
-    avahi freetype bitstream-vera-fonts \
-    ${PYTHON_COMPILE_DEPS} || true > /dev/null 2>&1
-yum -y install ${MANYLINUX1_DEPS}
-yum -y clean all > /dev/null 2>&1
-yum list installed
-
+if [ "$(uname -m)" != "s390x" ] ; then
+    yum -y erase wireless-tools gtk2 libX11 hicolor-icon-theme \
+        avahi freetype bitstream-vera-fonts \
+        ${PYTHON_COMPILE_DEPS} || true > /dev/null 2>&1
+    yum -y install ${MANYLINUX1_DEPS}
+    yum -y clean all > /dev/null 2>&1
+    yum list installed
+else
+    apt purge -y ${PYTHON_COMPILE_DEPS} || true > /dev/null 2>&1
+fi
 # we don't need libpython*.a, and they're many megabytes
 find /opt/_internal -name '*.a' -print0 | xargs -0 rm -f
 # Strip what we can -- and ignore errors, because this just attempts to strip

.ci/docker/requirements-ci.txt

@@ -36,7 +36,7 @@ expecttest==0.2.1
 #Pinned versions: 0.2.1
 #test that import:
 
-fbscribelogger==0.1.7
+fbscribelogger==0.1.6
 #Description: write to scribe from authenticated jobs on CI
 #Pinned versions: 0.1.6
 #test that import:
@@ -90,7 +90,7 @@ librosa>=0.6.2 ; python_version < "3.11"
 #Pinned versions:
 #test that import:
 
-mypy==1.13.0
+mypy==1.11.2
 # Pin MyPy version because new errors are likely to appear with each release
 #Description: linter
 #Pinned versions: 1.10.0
@@ -132,9 +132,6 @@ numpy==1.22.4; python_version == "3.9" or python_version == "3.10"
 numpy==1.26.2; python_version == "3.11" or python_version == "3.12"
 numpy==2.1.2; python_version >= "3.13"
 
-pandas==2.0.3; python_version < "3.13"
-pandas==2.2.3; python_version >= "3.13"
-
 #onnxruntime
 #Description: scoring engine for Open Neural Network Exchange (ONNX) models
 #Pinned versions: 1.9.0
@@ -158,7 +155,7 @@ optree==0.13.0
 #test_pointwise_ops.py, test_dtensor_ops.py, test_torchinductor.py, test_fx.py,
 #test_fake_tensor.py, test_mps.py
 
-pillow==11.0.0
+pillow==10.3.0
 #Description:  Python Imaging Library fork
 #Pinned versions: 10.3.0
 #test that import:
@@ -193,11 +190,6 @@ pytest-rerunfailures>=10.3
 #Pinned versions:
 #test that import:
 
-pytest-subtests==0.13.1
-#Description: plugin for subtest support
-#Pinned versions:
-#test that import:
-
 #pytest-benchmark
 #Description: fixture for benchmarking code
 #Pinned versions: 3.2.3
@@ -213,6 +205,11 @@ xdoctest==1.1.0
 #Pinned versions: 1.1.0
 #test that import:
 
+pydot==3.0.1
+#Description: Needed for testing FxGraphDrawer
+#Pinned versions:
+#test that import:
+
 pygments==2.15.0
 #Description: support doctest highlighting
 #Pinned versions: 2.12.0
@@ -245,7 +242,7 @@ scikit-image==0.22.0 ; python_version >= "3.10"
 #test that import:
 
 scipy==1.10.1 ; python_version <= "3.11"
-scipy==1.14.1 ; python_version >= "3.12"
+scipy==1.12.0 ; python_version == "3.12"
 # Pin SciPy because of failing distribution tests (see #60347)
 #Description: scientific python
 #Pinned versions: 1.10.1
@@ -289,6 +286,11 @@ redis>=4.0.0
 #Description: redis database
 #test that import: anything that tests OSS caching/mocking (inductor/test_codecache.py, inductor/test_max_autotune.py)
 
+rockset==1.0.3
+#Description: queries Rockset
+#Pinned versions: 1.0.3
+#test that import:
+
 ghstack==0.8.0
 #Description: ghstack tool
 #Pinned versions: 0.8.0
@@ -309,20 +311,19 @@ z3-solver==4.12.2.0
 #Pinned versions:
 #test that import:
 
-tensorboard==2.13.0 ; python_version < "3.13"
-tensorboard==2.18.0 ; python_version >= "3.13"
+tensorboard==2.13.0
 #Description: Also included in .ci/docker/requirements-docs.txt
 #Pinned versions:
 #test that import: test_tensorboard
 
 pywavelets==1.4.1 ; python_version < "3.12"
-pywavelets==1.7.0 ; python_version >= "3.12"
+pywavelets==1.5.0 ; python_version >= "3.12"
 #Description: This is a requirement of scikit-image, we need to pin
 # it here because 1.5.0 conflicts with numpy 1.21.2 used in CI
 #Pinned versions: 1.4.1
 #test that import:
 
-lxml==5.3.0
+lxml==5.0.0
 #Description: This is a requirement of unittest-xml-reporting
 
 # Python-3.9 binaries

.ci/docker/requirements-docs.txt

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

.ci/docker/triton_version.txt

@@ -1 +1 @@
-3.2.0
+3.1.0

.ci/docker/ubuntu-cuda/Dockerfile

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

.ci/docker/ubuntu/Dockerfile

@@ -36,8 +36,7 @@ ENV DOCS=$DOCS
 COPY requirements-ci.txt requirements-docs.txt /opt/conda/
 COPY ./common/install_conda.sh install_conda.sh
 COPY ./common/common_utils.sh common_utils.sh
-COPY ./common/install_magma_conda.sh install_magma_conda.sh
-RUN bash ./install_conda.sh && rm install_conda.sh install_magma_conda.sh common_utils.sh /opt/conda/requirements-ci.txt /opt/conda/requirements-docs.txt
+RUN bash ./install_conda.sh && rm install_conda.sh common_utils.sh /opt/conda/requirements-ci.txt /opt/conda/requirements-docs.txt
 RUN if [ -n "${UNINSTALL_DILL}" ]; then pip uninstall -y dill; fi
 
 # Install gcc
@@ -171,6 +170,13 @@ RUN if [ -n "${ACL}" ]; then bash ./install_acl.sh; fi
 RUN rm install_acl.sh
 ENV INSTALLED_ACL ${ACL}
 
+# (optional) install graphviz
+ARG GRAPHVIZ
+COPY ./common/install_graphviz.sh install_graphviz.sh
+RUN if [ -n "${GRAPHVIZ}" ]; then bash ./install_graphviz.sh; fi
+RUN rm install_graphviz.sh
+ENV INSTALLED_GRAPHVIZ ${GRAPHVIZ}
+
 # Install ccache/sccache (do this last, so we get priority in PATH)
 ARG SKIP_SCCACHE_INSTALL
 COPY ./common/install_cache.sh install_cache.sh

.ci/magma/.gitignore

@@ -1,2 +0,0 @@
-output/
-magma-cuda*/

.ci/magma/Makefile

@@ -1,48 +0,0 @@
-SHELL=/usr/bin/env bash
-
-DOCKER_CMD ?= docker
-DESIRED_CUDA ?= 11.8
-DESIRED_CUDA_SHORT = $(subst .,,$(DESIRED_CUDA))
-PACKAGE_NAME = magma-cuda
-CUDA_ARCH_LIST ?= -gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86 -gencode arch=compute_90,code=sm_90
-
-DOCKER_RUN = set -eou pipefail; ${DOCKER_CMD} run --rm -i \
-	-v $(shell git rev-parse --show-toplevel)/.ci:/builder \
-	-w /builder \
-	-e PACKAGE_NAME=${PACKAGE_NAME}${DESIRED_CUDA_SHORT} \
-	-e DESIRED_CUDA=${DESIRED_CUDA} \
-	-e CUDA_ARCH_LIST="${CUDA_ARCH_LIST}" \
-	"pytorch/manylinux-builder:cuda${DESIRED_CUDA}-main" \
-	magma/build_magma.sh
-
-.PHONY: all
-all: magma-cuda126
-all: magma-cuda124
-all: magma-cuda121
-all: magma-cuda118
-
-.PHONY:
-clean:
-	$(RM) -r magma-*
-	$(RM) -r output
-
-.PHONY: magma-cuda126
-magma-cuda126: DESIRED_CUDA := 12.6
-magma-cuda126:
-	$(DOCKER_RUN)
-
-.PHONY: magma-cuda124
-magma-cuda124: DESIRED_CUDA := 12.4
-magma-cuda124:
-	$(DOCKER_RUN)
-
-.PHONY: magma-cuda121
-magma-cuda121: DESIRED_CUDA := 12.1
-magma-cuda121:
-	$(DOCKER_RUN)
-
-.PHONY: magma-cuda118
-magma-cuda118: DESIRED_CUDA := 11.8
-magma-cuda118: CUDA_ARCH_LIST += -gencode arch=compute_37,code=sm_37
-magma-cuda118:
-	$(DOCKER_RUN)

.ci/magma/README.md

@@ -1,50 +0,0 @@
-# Magma
-
-This folder contains the scripts and configurations to build magma, statically linked for various versions of CUDA.
-
-## Building
-
-Look in the `Makefile` for available targets to build. To build any target, for example `magma-cuda118`, run
-
-```
-# Using `docker`
-make magma-cuda118
-
-# Using `podman`
-DOCKER_CMD=podman make magma-cuda118
-```
-
-This spawns a `pytorch/manylinux-cuda<version>` docker image, which has the required `devtoolset` and CUDA versions installed.
-Within the docker image, it runs `build_magma.sh` with the correct environment variables set, which package the necessary files
-into a tarball, with the following structure:
-
-```
-.
-├── include       # header files
-├── lib           # libmagma.a
-├── info
-│   ├── licenses  # license file
-│   └── recipe    # build script and patches
-```
-
-More specifically, `build_magma.sh` copies over the relevant files from the `package_files` directory depending on the CUDA version.
-Outputted binaries should be in the `output` folder.
-
-
-## Pushing
-
-Packages can be uploaded to an S3 bucket using:
-
-```
-aws s3 cp output/*/magma-cuda*.bz2 <bucket-with-path>
-```
-
-If you do not have upload permissions, please ping @seemethere or @soumith to gain access
-
-## New versions
-
-New CUDA versions can be added by creating a new make target with the next desired version. For CUDA version NN.n, the target should be named `magma-cudaNNn`.
-
-Make sure to edit the appropriate environment variables (e.g., DESIRED_CUDA, CUDA_ARCH_LIST) in the `Makefile` accordingly. Remember also to check `build_magma.sh` to ensure the logic for copying over the files remains correct.
-
-New patches can be added by editing `Makefile` and`build_magma.sh` the same way `getrf_nbparam.patch` is implemented.

.ci/magma/build_magma.sh

@@ -1,50 +0,0 @@
-#!/usr/bin/env bash
-
-set -eou pipefail
-
-# Environment variables
-# The script expects DESIRED_CUDA and PACKAGE_NAME to be set
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-MAGMA_VERSION=2.6.1
-
-# Folders for the build
-PACKAGE_FILES=${ROOT_DIR}/magma/package_files # source patches and metadata
-PACKAGE_DIR=${ROOT_DIR}/magma/${PACKAGE_NAME} # build workspace
-PACKAGE_OUTPUT=${ROOT_DIR}/magma/output # where tarballs are stored
-PACKAGE_BUILD=${PACKAGE_DIR}/build # where the content of the tarball is prepared
-PACKAGE_RECIPE=${PACKAGE_BUILD}/info/recipe
-PACKAGE_LICENSE=${PACKAGE_BUILD}/info/licenses
-mkdir -p ${PACKAGE_DIR} ${PACKAGE_OUTPUT}/linux-64 ${PACKAGE_BUILD} ${PACKAGE_RECIPE} ${PACKAGE_LICENSE}
-
-# Fetch magma sources and verify checksum
-pushd ${PACKAGE_DIR}
-curl -LO http://icl.utk.edu/projectsfiles/magma/downloads/magma-${MAGMA_VERSION}.tar.gz
-tar zxf magma-${MAGMA_VERSION}.tar.gz
-sha256sum --check < ${PACKAGE_FILES}/magma-${MAGMA_VERSION}.sha256
-popd
-
-# Apply patches and build
-pushd ${PACKAGE_DIR}/magma-${MAGMA_VERSION}
-patch < ${PACKAGE_FILES}/CMake.patch
-patch < ${PACKAGE_FILES}/cmakelists.patch
-patch -p0 < ${PACKAGE_FILES}/thread_queue.patch
-patch -p1 < ${PACKAGE_FILES}/getrf_shfl.patch
-patch -p1 < ${PACKAGE_FILES}/getrf_nbparam.patch
-# The build.sh script expects to be executed from the sources root folder
-INSTALL_DIR=${PACKAGE_BUILD} ${PACKAGE_FILES}/build.sh
-popd
-
-# Package recipe, license and tarball
-# Folder and package name are backward compatible for the build workflow
-cp ${PACKAGE_FILES}/build.sh ${PACKAGE_RECIPE}/build.sh
-cp ${PACKAGE_FILES}/thread_queue.patch ${PACKAGE_RECIPE}/thread_queue.patch
-cp ${PACKAGE_FILES}/cmakelists.patch ${PACKAGE_RECIPE}/cmakelists.patch
-cp ${PACKAGE_FILES}/getrf_shfl.patch ${PACKAGE_RECIPE}/getrf_shfl.patch
-cp ${PACKAGE_FILES}/getrf_nbparam.patch ${PACKAGE_RECIPE}/getrf_nbparam.patch
-cp ${PACKAGE_FILES}/CMake.patch ${PACKAGE_RECIPE}/CMake.patch
-cp ${PACKAGE_FILES}/magma-${MAGMA_VERSION}.sha256 ${PACKAGE_RECIPE}/magma-${MAGMA_VERSION}.sha256
-cp ${PACKAGE_DIR}/magma-${MAGMA_VERSION}/COPYRIGHT ${PACKAGE_LICENSE}/COPYRIGHT
-pushd ${PACKAGE_BUILD}
-tar cjf ${PACKAGE_OUTPUT}/linux-64/${PACKAGE_NAME}-${MAGMA_VERSION}-1.tar.bz2 include lib info
-echo Built in ${PACKAGE_OUTPUT}/linux-64/${PACKAGE_NAME}-${MAGMA_VERSION}-1.tar.bz2
-popd

.ci/magma/package_files/CMake.patch

@@ -1,40 +0,0 @@
---- CMake.src.cuda	2023-03-29 10:05:32.136954140 +0000
-+++ CMake.src.cuda	2023-03-29 10:05:50.281318043 +0000
-@@ -283,10 +283,10 @@
- magmablas/zgeadd.cu
- magmablas/zgeadd2.cu
- magmablas/zgeam.cu
--magmablas/zgemm_fermi.cu
-+#magmablas/zgemm_fermi.cu
- magmablas/zgemm_reduce.cu
- magmablas/zgemv_conj.cu
--magmablas/zgemv_fermi.cu
-+#magmablas/zgemv_fermi.cu
- magmablas/zgerbt.cu
- magmablas/zgerbt_kernels.cu
- magmablas/zgetmatrix_transpose.cpp
-@@ -1009,18 +1009,18 @@
- magmablas/sgeam.cu
- magmablas/dgeam.cu
- magmablas/cgeam.cu
--magmablas/sgemm_fermi.cu
--magmablas/dgemm_fermi.cu
--magmablas/cgemm_fermi.cu
-+#magmablas/sgemm_fermi.cu
-+#magmablas/dgemm_fermi.cu
-+#magmablas/cgemm_fermi.cu
- magmablas/sgemm_reduce.cu
- magmablas/dgemm_reduce.cu
- magmablas/cgemm_reduce.cu
- magmablas/sgemv_conj.cu
- magmablas/dgemv_conj.cu
- magmablas/cgemv_conj.cu
--magmablas/sgemv_fermi.cu
--magmablas/dgemv_fermi.cu
--magmablas/cgemv_fermi.cu
-+#magmablas/sgemv_fermi.cu
-+#magmablas/dgemv_fermi.cu
-+#magmablas/cgemv_fermi.cu
- magmablas/sgerbt.cu
- magmablas/dgerbt.cu
- magmablas/cgerbt.cu

.ci/magma/package_files/build.sh

@@ -1,12 +0,0 @@
-CUDA__VERSION=$(nvcc --version|sed -n 4p|cut -f5 -d" "|cut -f1 -d",")
-if [ "$CUDA__VERSION" != "$DESIRED_CUDA" ]; then
-    echo "CUDA Version is not $DESIRED_CUDA. CUDA Version found: $CUDA__VERSION"
-    exit 1
-fi
-
-mkdir build
-cd build
-cmake .. -DUSE_FORTRAN=OFF -DGPU_TARGET="All" -DCMAKE_INSTALL_PREFIX="$INSTALL_DIR" -DCUDA_ARCH_LIST="$CUDA_ARCH_LIST"
-make -j$(getconf _NPROCESSORS_CONF)
-make install
-cd ..

.ci/magma/package_files/cmakelists.patch

@@ -1,388 +0,0 @@
-diff --git a/CMakeLists.txt b/CMakeLists.txt
-index d5d8d87d..8a507334 100644
---- a/CMakeLists.txt
-+++ b/CMakeLists.txt
-@@ -3,7 +3,7 @@ cmake_minimum_required( VERSION 2.8.1 )
- # ----------------------------------------
- # to disable Fortran, set this to "off"
- # see also -DADD_ below
--option( USE_FORTRAN "Fortran is required for some tester checks, but can be disabled with reduced functionality" ON )
-+option( USE_FORTRAN "Fortran is required for some tester checks, but can be disabled with reduced functionality" OFF )
-
- if (USE_FORTRAN)
-     project( MAGMA C CXX Fortran )
-@@ -75,6 +75,8 @@ else()
-     message( WARNING "The compiler ${CMAKE_CXX_COMPILER} doesn't support the -std=c++11 flag. Some code may not compile.")
- endif()
-
-+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -static-libstdc++ -fno-exceptions")
-+
- CHECK_C_COMPILER_FLAG("-std=c99" COMPILER_SUPPORTS_C99)
- if (COMPILER_SUPPORTS_C99)
-     set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=c99")
-@@ -101,15 +103,15 @@ endif()
-
-
- # ----------------------------------------
--# locate OpenMP
--find_package( OpenMP )
--if (OPENMP_FOUND)
--    message( STATUS "Found OpenMP" )
--    message( STATUS "    OpenMP_C_FLAGS   ${OpenMP_C_FLAGS}" )
--    message( STATUS "    OpenMP_CXX_FLAGS ${OpenMP_CXX_FLAGS}" )
--    set( CMAKE_C_FLAGS   "${CMAKE_C_FLAGS} ${OpenMP_C_FLAGS}" )
--    set( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}" )
--endif()
-+# # locate OpenMP
-+# find_package( OpenMP )
-+# if (OPENMP_FOUND)
-+#     message( STATUS "Found OpenMP" )
-+#     message( STATUS "    OpenMP_C_FLAGS   ${OpenMP_C_FLAGS}" )
-+#     message( STATUS "    OpenMP_CXX_FLAGS ${OpenMP_CXX_FLAGS}" )
-+#     set( CMAKE_C_FLAGS   "${CMAKE_C_FLAGS} ${OpenMP_C_FLAGS}" )
-+#     set( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}" )
-+# endif()
-
- if (MAGMA_ENABLE_CUDA)
-   # ----------------------------------------
-@@ -132,7 +134,7 @@ if (MAGMA_ENABLE_CUDA)
-     set( NV_SM    "" )
-     set( NV_COMP  "" )
-
--    set(CUDA_SEPARABLE_COMPILATION ON)
-+    set(CUDA_SEPARABLE_COMPILATION OFF)
-
-     # nvcc >= 6.5 supports -std=c++11, so propagate CXXFLAGS to NVCCFLAGS.
-     # Older nvcc didn't support -std=c++11, so previously we disabled propagation.
-@@ -294,11 +296,18 @@ if (MAGMA_ENABLE_CUDA)
-         message( STATUS "    compile for CUDA arch 8.0 (Ampere)" )
-     endif()
-
-+    if ( ${GPU_TARGET} MATCHES "All")
-+        set( MIN_ARCH 370)
-+        SET( NV_SM ${CUDA_ARCH_LIST})
-+        SET( NV_COMP "")
-+    endif()
-+
-     if (NOT MIN_ARCH)
-         message( FATAL_ERROR "GPU_TARGET must contain one or more of Fermi, Kepler, Maxwell, Pascal, Volta, Turing, Ampere, or valid sm_[0-9][0-9]" )
-     endif()
-
--    set( CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} -Xcompiler -fPIC ${NV_SM} ${NV_COMP} ${FORTRAN_CONVENTION} )
-+    set( CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} -DHAVE_CUBLAS -Xfatbin -compress-all -Xcompiler -fPIC -std=c++11 ${NV_SM} ${NV_COMP} ${FORTRAN_CONVENTION} )
-+    MESSAGE(STATUS "CUDA_NVCC_FLAGS: ${CUDA_NVCC_FLAGS}")
-     #add_definitions( "-DMAGMA_HAVE_CUDA -DMAGMA_CUDA_ARCH_MIN=${MIN_ARCH}" )
-     set(MAGMA_HAVE_CUDA "1")
-     set(MAGMA_CUDA_ARCH_MIN "${MIN_ARCH}")
-@@ -413,7 +422,7 @@ set_property(CACHE BLA_VENDOR PROPERTY STRINGS
- set( LAPACK_LIBRARIES "" CACHE STRING "Libraries for LAPACK and BLAS, to manually override search" )
- if (LAPACK_LIBRARIES STREQUAL "")
-     message( STATUS "Searching for BLAS and LAPACK. To override, set LAPACK_LIBRARIES using ccmake." )
--    find_package( LAPACK )
-+    # find_package( LAPACK )
-     # force showing updated LAPACK_LIBRARIES in ccmake / cmake-gui.
-     set( LAPACK_LIBRARIES ${LAPACK_LIBRARIES} CACHE STRING "Libraries for LAPACK and BLAS, to manually override search" FORCE )
- else()
-@@ -552,12 +561,12 @@ if (WIN32)
-     #message( "libmagma_all_f   ${libmagma_all_f}"   )
-
-     # on Windows, Fortran files aren't compiled if listed here...
--    cuda_add_library( magma ${libmagma_all_cpp} )
-+    cuda_add_library( magma STATIC ${libmagma_all_cpp} OPTIONS --compiler-options "-fPIC")
-     target_link_libraries( magma
-         ${LAPACK_LIBRARIES}
-         ${CUDA_CUDART_LIBRARY}
-         ${CUDA_CUBLAS_LIBRARIES}
--        ${CUDA_cusparse_LIBRARY}
-+        # ${CUDA_cusparse_LIBRARY}
-     )
-
-     # no Fortran files at the moment (how to test libmagma_all_f is not empty?),
-@@ -575,13 +584,13 @@ if (WIN32)
- else()
-     # Unix doesn't seem to have a problem with mixing C, CUDA, and Fortran files
-     if (MAGMA_ENABLE_CUDA)
--      cuda_add_library( magma ${libmagma_all} )
-+      cuda_add_library( magma STATIC ${libmagma_all} OPTIONS --compiler-options "-fPIC")
-       target_link_libraries( magma
-         ${blas_fix}
-         ${LAPACK_LIBRARIES}
-         ${CUDA_CUDART_LIBRARY}
-         ${CUDA_CUBLAS_LIBRARIES}
--        ${CUDA_cusparse_LIBRARY}
-+        # ${CUDA_cusparse_LIBRARY}
- 	)
-     else()
-       find_package( hipBLAS )
-@@ -614,138 +623,139 @@ else()
-     endif()
- endif()
- add_custom_target( lib DEPENDS magma )
--
--
--# ----------------------------------------
--# compile lapacktest library
--# If use fortran, compile only Fortran files, not magma_[sdcz]_no_fortran.cpp
--# else,           compile only C++     files, not Fortran files
--if (USE_FORTRAN)
--    foreach( filename ${liblapacktest_all} )
--        if (filename MATCHES "\\.(f|f90|F90)$")
--            list( APPEND liblapacktest_all_f ${filename} )
--        endif()
--    endforeach()
--    add_library( lapacktest ${liblapacktest_all_f} )
--else()
--    # alternatively, use only C/C++/CUDA files, including magma_[sdcz]_no_fortran.cpp
--    foreach( filename ${liblapacktest_all} )
--        if (filename MATCHES "\\.(c|cu|cpp)$")
--            list( APPEND liblapacktest_all_cpp ${filename} )
--        endif()
--    endforeach()
--    add_library( lapacktest ${liblapacktest_all_cpp} )
--endif()
--target_link_libraries( lapacktest
--    ${blas_fix}
--    ${LAPACK_LIBRARIES}
--)
--
--
--# ----------------------------------------
--# compile tester library
--add_library( tester ${libtest_all} )
--target_link_libraries( tester
--    magma
--    lapacktest
--    ${blas_fix}
--    ${LAPACK_LIBRARIES}
--)
-+set_target_properties(magma PROPERTIES POSITION_INDEPENDENT_CODE ON)
-+
-+
-+# # ----------------------------------------
-+# # compile lapacktest library
-+# # If use fortran, compile only Fortran files, not magma_[sdcz]_no_fortran.cpp
-+# # else,           compile only C++     files, not Fortran files
-+# if (USE_FORTRAN)
-+#     foreach( filename ${liblapacktest_all} )
-+#         if (filename MATCHES "\\.(f|f90|F90)$")
-+#             list( APPEND liblapacktest_all_f ${filename} )
-+#         endif()
-+#     endforeach()
-+#     add_library( lapacktest ${liblapacktest_all_f} )
-+# else()
-+#     # alternatively, use only C/C++/CUDA files, including magma_[sdcz]_no_fortran.cpp
-+#     foreach( filename ${liblapacktest_all} )
-+#         if (filename MATCHES "\\.(c|cu|cpp)$")
-+#             list( APPEND liblapacktest_all_cpp ${filename} )
-+#         endif()
-+#     endforeach()
-+#     add_library( lapacktest ${liblapacktest_all_cpp} )
-+# endif()
-+# target_link_libraries( lapacktest
-+#     ${blas_fix}
-+#     ${LAPACK_LIBRARIES}
-+# )
-+
-+
-+# # ----------------------------------------
-+# # compile tester library
-+# add_library( tester ${libtest_all} )
-+# target_link_libraries( tester
-+#     magma
-+#     lapacktest
-+#     ${blas_fix}
-+#     ${LAPACK_LIBRARIES}
-+# )
-
-
- # ----------------------------------------
- # compile MAGMA sparse library
-
- # sparse doesn't have Fortran at the moment, so no need for above shenanigans
--if (MAGMA_ENABLE_CUDA)
--  include_directories( sparse/include )
--  include_directories( sparse/control )
--else()
--  include_directories( sparse_hip/include )
--  include_directories( sparse_hip/control )
--endif()
--include_directories( testing )
--
--if (MAGMA_ENABLE_CUDA)
--  cuda_add_library( magma_sparse ${libsparse_all} )
--  target_link_libraries( magma_sparse
--    magma
--    ${blas_fix}
--    ${LAPACK_LIBRARIES}
--    ${CUDA_CUDART_LIBRARY}
--    ${CUDA_CUBLAS_LIBRARIES}
--    ${CUDA_cusparse_LIBRARY}
--    )
--else()
--  add_library( magma_sparse ${libsparse_all} )
--  target_link_libraries( magma_sparse
--    magma
--    ${blas_fix}
--    ${LAPACK_LIBRARIES}
--    hip::device
--    roc::hipblas
--    roc::hipsparse
--    )
--endif()
--add_custom_target( sparse-lib DEPENDS magma_sparse )
--
--
--# ----------------------------------------
--# compile each tester
--
--# save testers to testing/
--# save tester lib files to testing_lib/ to avoid cluttering lib/
--set( CMAKE_RUNTIME_OUTPUT_DIRECTORY testing )
--set( CMAKE_ARCHIVE_OUTPUT_DIRECTORY testing_lib )
--set( CMAKE_LIBRARY_OUTPUT_DIRECTORY testing_lib )
--
--# skip Fortran testers, which require an extra file from CUDA
--foreach( filename ${testing_all} )
--    if (filename MATCHES "\\.(c|cu|cpp)$")
--        list( APPEND testing_all_cpp ${filename} )
--    endif()
--endforeach()
--foreach( TEST ${testing_all_cpp} )
--    string( REGEX REPLACE "\\.(cpp|f90|F90)" "" EXE ${TEST} )
--    string( REGEX REPLACE "testing/" "" EXE ${EXE} )
--    #message( "${TEST} --> ${EXE}" )
--    add_executable( ${EXE} ${TEST} )
--    target_link_libraries( ${EXE} tester lapacktest magma )
--    list( APPEND testing ${EXE} )
--endforeach()
--add_custom_target( testing DEPENDS ${testing} )
--
--
--# ----------------------------------------
--# compile each sparse tester
--
--if (MAGMA_ENABLE_CUDA)
--  set(SPARSE_TEST_DIR "sparse/testing")
--else()
--  set(SPARSE_TEST_DIR "sparse_hip/testing")
--endif()
--
--
--set( CMAKE_RUNTIME_OUTPUT_DIRECTORY "${SPARSE_TEST_DIR}" )
--cmake_policy( SET CMP0037 OLD)
--foreach( TEST ${sparse_testing_all} )
--    string( REGEX REPLACE "\\.(cpp|f90|F90)"     "" EXE ${TEST} )
--    string( REGEX REPLACE "${SPARSE_TEST_DIR}/" "" EXE ${EXE} )
--    #message( "${TEST} --> ${EXE}" )
--    add_executable( ${EXE} ${TEST} )
--    target_link_libraries( ${EXE} magma_sparse magma )
--    list( APPEND sparse-testing ${EXE} )
--endforeach()
--add_custom_target( sparse-testing DEPENDS ${sparse-testing} )
-+# if (MAGMA_ENABLE_CUDA)
-+#   include_directories( sparse/include )
-+#   include_directories( sparse/control )
-+# else()
-+#   include_directories( sparse_hip/include )
-+#   include_directories( sparse_hip/control )
-+# endif()
-+# include_directories( testing )
-+
-+# if (MAGMA_ENABLE_CUDA)
-+#   cuda_add_library( magma_sparse ${libsparse_all} )
-+#   target_link_libraries( magma_sparse
-+#     magma
-+#     ${blas_fix}
-+#     ${LAPACK_LIBRARIES}
-+#     ${CUDA_CUDART_LIBRARY}
-+#     ${CUDA_CUBLAS_LIBRARIES}
-+#     ${CUDA_cusparse_LIBRARY}
-+#     )
-+# else()
-+#   add_library( magma_sparse ${libsparse_all} )
-+#   target_link_libraries( magma_sparse
-+#     magma
-+#     ${blas_fix}
-+#     ${LAPACK_LIBRARIES}
-+#     hip::device
-+#     roc::hipblas
-+#     roc::hipsparse
-+#     )
-+# endif()
-+# add_custom_target( sparse-lib DEPENDS magma_sparse )
-+
-+
-+# # ----------------------------------------
-+# # compile each tester
-+
-+# # save testers to testing/
-+# # save tester lib files to testing_lib/ to avoid cluttering lib/
-+# set( CMAKE_RUNTIME_OUTPUT_DIRECTORY testing )
-+# set( CMAKE_ARCHIVE_OUTPUT_DIRECTORY testing_lib )
-+# set( CMAKE_LIBRARY_OUTPUT_DIRECTORY testing_lib )
-+
-+# # skip Fortran testers, which require an extra file from CUDA
-+# foreach( filename ${testing_all} )
-+#     if (filename MATCHES "\\.(c|cu|cpp)$")
-+#         list( APPEND testing_all_cpp ${filename} )
-+#     endif()
-+# endforeach()
-+# foreach( TEST ${testing_all_cpp} )
-+#     string( REGEX REPLACE "\\.(cpp|f90|F90)" "" EXE ${TEST} )
-+#     string( REGEX REPLACE "testing/" "" EXE ${EXE} )
-+#     #message( "${TEST} --> ${EXE}" )
-+#     add_executable( ${EXE} ${TEST} )
-+#     target_link_libraries( ${EXE} tester lapacktest magma )
-+#     list( APPEND testing ${EXE} )
-+# endforeach()
-+# add_custom_target( testing DEPENDS ${testing} )
-+
-+
-+# # ----------------------------------------
-+# # compile each sparse tester
-+
-+# if (MAGMA_ENABLE_CUDA)
-+#   set(SPARSE_TEST_DIR "sparse/testing")
-+# else()
-+#   set(SPARSE_TEST_DIR "sparse_hip/testing")
-+# endif()
-+
-+
-+# set( CMAKE_RUNTIME_OUTPUT_DIRECTORY "${SPARSE_TEST_DIR}" )
-+# cmake_policy( SET CMP0037 OLD)
-+# foreach( TEST ${sparse_testing_all} )
-+#     string( REGEX REPLACE "\\.(cpp|f90|F90)"     "" EXE ${TEST} )
-+#     string( REGEX REPLACE "${SPARSE_TEST_DIR}/" "" EXE ${EXE} )
-+#     #message( "${TEST} --> ${EXE}" )
-+#     add_executable( ${EXE} ${TEST} )
-+#     target_link_libraries( ${EXE} magma_sparse magma )
-+#     list( APPEND sparse-testing ${EXE} )
-+# endforeach()
-+# add_custom_target( sparse-testing DEPENDS ${sparse-testing} )
-
-
- # ----------------------------------------
- # what to install
--install( TARGETS magma magma_sparse ${blas_fix}
-+install( TARGETS magma ${blas_fix}
-          RUNTIME DESTINATION bin
-          LIBRARY DESTINATION lib
-          ARCHIVE DESTINATION lib )
--file( GLOB headers include/*.h sparse/include/*.h "${CMAKE_BINARY_DIR}/include/*.h" )
-+file( GLOB headers include/*.h "${CMAKE_BINARY_DIR}/include/*.h" )
- if (USE_FORTRAN)
-     install( FILES ${headers} ${modules}
-              DESTINATION include )
-@@ -769,9 +779,9 @@ else()
-     "${blas_fix_lib} ${LAPACK_LIBS} hip::device roc::hipblas roc::hipsparse" )
- endif()
- set( MAGMA_REQUIRED "" )
--configure_file( "${pkgconfig}.in" "${pkgconfig}" @ONLY )
--install( FILES "${CMAKE_BINARY_DIR}/${pkgconfig}"
--         DESTINATION lib/pkgconfig )
-+# configure_file( "${pkgconfig}.in" "${pkgconfig}" @ONLY )
-+# install( FILES "${CMAKE_BINARY_DIR}/${pkgconfig}"
-+#          DESTINATION lib/pkgconfig )
-
- # ----------------------------------------
- get_directory_property( compile_definitions COMPILE_DEFINITIONS )

.ci/magma/package_files/getrf_nbparam.patch

@@ -1,40 +0,0 @@
-diff --git a/control/get_batched_crossover.cpp b/control/get_batched_crossover.cpp
-index 4ec57306..912f8608 100644
---- a/control/get_batched_crossover.cpp
-+++ b/control/get_batched_crossover.cpp
-@@ -119,7 +119,7 @@ void magma_get_spotrf_batched_nbparam(magma_int_t n, magma_int_t *nb, magma_int_
- void magma_get_zgetrf_batched_nbparam(magma_int_t n, magma_int_t *nb, magma_int_t *recnb)
- {
-     *nb    = 64;
--    *recnb = 32;
-+    *recnb = 16;
-     return;
- }
- 
-@@ -127,7 +127,7 @@ void magma_get_zgetrf_batched_nbparam(magma_int_t n, magma_int_t *nb, magma_int_
- void magma_get_cgetrf_batched_nbparam(magma_int_t n, magma_int_t *nb, magma_int_t *recnb)
- {
-     *nb    = 128;
--    *recnb =  32;
-+    *recnb =  16;
-     return;
- }
- 
-@@ -135,7 +135,7 @@ void magma_get_cgetrf_batched_nbparam(magma_int_t n, magma_int_t *nb, magma_int_
- void magma_get_dgetrf_batched_nbparam(magma_int_t n, magma_int_t *nb, magma_int_t *recnb)
- {
-     *nb    = 128;
--    *recnb =  32;
-+    *recnb =  16;
-     return;
- }
- 
-@@ -143,7 +143,7 @@ void magma_get_dgetrf_batched_nbparam(magma_int_t n, magma_int_t *nb, magma_int_
- void magma_get_sgetrf_batched_nbparam(magma_int_t n, magma_int_t *nb, magma_int_t *recnb)
- {
-     *nb    = 128;
--    *recnb =  32;
-+    *recnb =  16;
-     return;
- }
- 

.ci/magma/package_files/getrf_shfl.patch

@@ -1,15 +0,0 @@
-diff --git a/src/zgetrf_batched.cpp b/src/zgetrf_batched.cpp
-index 24a65a90..884d9352 100644
---- a/src/zgetrf_batched.cpp
-+++ b/src/zgetrf_batched.cpp
-@@ -116,7 +116,9 @@ magma_zgetrf_batched(
-             return magma_zgetrf_batched_smallsq_noshfl( m, dA_array, ldda, ipiv_array, info_array, batchCount, queue );
-         }
-         else{
--            return magma_zgetrf_batched_smallsq_shfl( m, dA_array, ldda, ipiv_array, info_array, batchCount, queue );
-+            // magma_cgetrf_batched_smallsq_shfl is broken, therefore let's call noshfl version for arch < 700
-+            // return magma_zgetrf_batched_smallsq_shfl( m, dA_array, ldda, ipiv_array, info_array, batchCount, queue );
-+            return magma_zgetrf_batched_smallsq_noshfl( m, dA_array, ldda, ipiv_array, info_array, batchCount, queue );
-         }
-         #else
-         return magma_zgetrf_batched_smallsq_noshfl( m, dA_array, ldda, ipiv_array, info_array, batchCount, queue );

.ci/magma/package_files/magma-2.6.1.sha256

@@ -1 +0,0 @@
-6cd83808c6e8bc7a44028e05112b3ab4e579bcc73202ed14733f66661127e213  magma-2.6.1.tar.gz

.ci/magma/package_files/thread_queue.patch

@@ -1,20 +0,0 @@
---- control/thread_queue.cpp	2016-08-30 06:37:49.000000000 -0700
-+++ control/thread_queue.cpp	2016-10-10 19:47:28.911580965 -0700
-@@ -15,7 +15,7 @@
- {
-     if ( err != 0 ) {
-         fprintf( stderr, "Error: %s (%d)\n", strerror(err), err );
--        throw std::exception();
-+        // throw std::exception();
-     }
- }
- 
-@@ -172,7 +172,7 @@
-     check( pthread_mutex_lock( &mutex ));
-     if ( quit_flag ) {
-         fprintf( stderr, "Error: push_task() called after quit()\n" );
--        throw std::exception();
-+        // throw std::exception();
-     }
-     q.push( task );
-     ntask += 1;

.ci/manywheel/build.sh

@@ -15,12 +15,9 @@ case "${GPU_ARCH_TYPE:-BLANK}" in
     rocm)
         bash "${SCRIPTPATH}/build_rocm.sh"
         ;;
-    cpu | cpu-cxx11-abi | cpu-s390x)
+    cpu | cpu-cxx11-abi | cpu-s390x | xpu)
         bash "${SCRIPTPATH}/build_cpu.sh"
         ;;
-    xpu)
-        bash "${SCRIPTPATH}/build_xpu.sh"
-        ;;
     *)
         echo "Un-recognized GPU_ARCH_TYPE '${GPU_ARCH_TYPE}', exiting..."
         exit 1

.ci/manywheel/build_common.sh

@@ -4,9 +4,12 @@
 set -ex
 SOURCE_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null && pwd )"
 
-source ${SOURCE_DIR}/set_desired_python.sh
-
 
+# Require only one python installation
+if [[ -z "$DESIRED_PYTHON" ]]; then
+    echo "Need to set DESIRED_PYTHON env variable"
+    exit 1
+fi
 if [[ -n "$BUILD_PYTHONLESS" && -z "$LIBTORCH_VARIANT" ]]; then
     echo "BUILD_PYTHONLESS is set, so need LIBTORCH_VARIANT to also be set"
     echo "LIBTORCH_VARIANT should be one of shared-with-deps shared-without-deps static-with-deps static-without-deps"
@@ -18,14 +21,12 @@ retry () {
     $*  || (sleep 1 && $*) || (sleep 2 && $*) || (sleep 4 && $*) || (sleep 8 && $*)
 }
 
-PLATFORM="manylinux2014_x86_64"
 # TODO move this into the Docker images
 OS_NAME=$(awk -F= '/^NAME/{print $2}' /etc/os-release)
 if [[ "$OS_NAME" == *"CentOS Linux"* ]]; then
     retry yum install -q -y zip openssl
 elif [[ "$OS_NAME" == *"AlmaLinux"* ]]; then
     retry yum install -q -y zip openssl
-    PLATFORM="manylinux_2_28_x86_64"
 elif [[ "$OS_NAME" == *"Red Hat Enterprise Linux"* ]]; then
     retry dnf install -q -y zip openssl
 elif [[ "$OS_NAME" == *"Ubuntu"* ]]; then
@@ -79,7 +80,27 @@ if [[ -e /opt/openssl ]]; then
     export CMAKE_INCLUDE_PATH="/opt/openssl/include":$CMAKE_INCLUDE_PATH
 fi
 
+# If given a python version like 3.6m or 2.7mu, convert this to the format we
+# expect. The binary CI jobs pass in python versions like this; they also only
+# ever pass one python version, so we assume that DESIRED_PYTHON is not a list
+# in this case
+if [[ -n "$DESIRED_PYTHON" && $DESIRED_PYTHON =~ ([0-9].[0-9]+)t ]]; then
+    python_digits="$(echo $DESIRED_PYTHON | tr -cd [:digit:])"
+    py_majmin="${DESIRED_PYTHON}"
+    DESIRED_PYTHON="cp${python_digits}-cp${python_digits}t"
+elif [[ -n "$DESIRED_PYTHON" && "$DESIRED_PYTHON" != cp* ]]; then
+    python_nodot="$(echo $DESIRED_PYTHON | tr -d m.u)"
+    DESIRED_PYTHON="cp${python_nodot}-cp${python_nodot}"
+    if [[ ${python_nodot} -ge 310 ]]; then
+        py_majmin="${DESIRED_PYTHON:2:1}.${DESIRED_PYTHON:3:2}"
+    else
+        py_majmin="${DESIRED_PYTHON:2:1}.${DESIRED_PYTHON:3:1}"
+    fi
+fi
 
+pydir="/opt/python/$DESIRED_PYTHON"
+export PATH="$pydir/bin:$PATH"
+echo "Will build for Python version: ${DESIRED_PYTHON} with ${python_installation}"
 
 mkdir -p /tmp/$WHEELHOUSE_DIR
 
@@ -255,11 +276,11 @@ make_wheel_record() {
     FPATH=$1
     if echo $FPATH | grep RECORD >/dev/null 2>&1; then
         # if the RECORD file, then
-        echo "\"$FPATH\",,"
+        echo "$FPATH,,"
     else
         HASH=$(openssl dgst -sha256 -binary $FPATH | openssl base64 | sed -e 's/+/-/g' | sed -e 's/\//_/g' | sed -e 's/=//g')
         FSIZE=$(ls -nl $FPATH | awk '{print $5}')
-        echo "\"$FPATH\",sha256=$HASH,$FSIZE"
+        echo "$FPATH,sha256=$HASH,$FSIZE"
     fi
 }
 
@@ -379,12 +400,6 @@ for pkg in /$WHEELHOUSE_DIR/torch_no_python*.whl /$WHEELHOUSE_DIR/torch*linux*.w
         $PATCHELF_BIN --print-rpath $sofile
     done
 
-    # create Manylinux 2_28 tag this needs to happen before regenerate the RECORD
-    if [[ $PLATFORM == "manylinux_2_28_x86_64" && $GPU_ARCH_TYPE != "cpu-s390x" && $GPU_ARCH_TYPE != "xpu" ]]; then
-        wheel_file=$(echo $(basename $pkg) | sed -e 's/-cp.*$/.dist-info\/WHEEL/g')
-        sed -i -e s#linux_x86_64#"${PLATFORM}"# $wheel_file;
-    fi
-
     # regenerate the RECORD file with new hashes
     record_file=$(echo $(basename $pkg) | sed -e 's/-cp.*$/.dist-info\/RECORD/g')
     if [[ -e $record_file ]]; then
@@ -424,20 +439,12 @@ for pkg in /$WHEELHOUSE_DIR/torch_no_python*.whl /$WHEELHOUSE_DIR/torch*linux*.w
         popd
     fi
 
-    # Rename wheel for Manylinux 2_28
-    if [[ $PLATFORM == "manylinux_2_28_x86_64" && $GPU_ARCH_TYPE != "cpu-s390x" && $GPU_ARCH_TYPE != "xpu" ]]; then
-        pkg_name=$(echo $(basename $pkg) | sed -e s#linux_x86_64#"${PLATFORM}"#)
-        zip -rq $pkg_name $PREIX*
-        rm -f $pkg
-        mv $pkg_name $(dirname $pkg)/$pkg_name
-    else
-        # zip up the wheel back
-        zip -rq $(basename $pkg) $PREIX*
-        # remove original wheel
-        rm -f $pkg
-        mv $(basename $pkg) $pkg
-    fi
+    # zip up the wheel back
+    zip -rq $(basename $pkg) $PREIX*
 
+    # replace original wheel
+    rm -f $pkg
+    mv $(basename $pkg) $pkg
     cd ..
     rm -rf tmp
 done

.ci/manywheel/build_cpu.sh

@@ -2,6 +2,8 @@
 
 set -ex
 
+GPU_ARCH_TYPE=${GPU_ARCH_TYPE:-cpu}
+
 export TH_BINARY_BUILD=1
 export USE_CUDA=0
 
@@ -15,13 +17,22 @@ if [[ -z "$EXTRA_CAFFE2_CMAKE_FLAGS" ]]; then
     EXTRA_CAFFE2_CMAKE_FLAGS=()
 fi
 
-WHEELHOUSE_DIR="wheelhousecpu"
-LIBTORCH_HOUSE_DIR="libtorch_housecpu"
+DIR_SUFFIX=cpu
+if [[ "$GPU_ARCH_TYPE" == "xpu" ]]; then
+    DIR_SUFFIX=xpu
+    # Refer https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpu/2-5.html
+    source /opt/intel/oneapi/pytorch-gpu-dev-0.5/oneapi-vars.sh
+    source /opt/intel/oneapi/pti/latest/env/vars.sh
+    export USE_STATIC_MKL=1
+fi
+
+WHEELHOUSE_DIR="wheelhouse$DIR_SUFFIX"
+LIBTORCH_HOUSE_DIR="libtorch_house$DIR_SUFFIX"
 if [[ -z "$PYTORCH_FINAL_PACKAGE_DIR" ]]; then
     if [[ -z "$BUILD_PYTHONLESS" ]]; then
-        PYTORCH_FINAL_PACKAGE_DIR="/remote/wheelhousecpu"
+        PYTORCH_FINAL_PACKAGE_DIR="/remote/wheelhouse$DIR_SUFFIX"
     else
-        PYTORCH_FINAL_PACKAGE_DIR="/remote/libtorch_housecpu"
+        PYTORCH_FINAL_PACKAGE_DIR="/remote/libtorch_house$DIR_SUFFIX"
     fi
 fi
 mkdir -p "$PYTORCH_FINAL_PACKAGE_DIR" || true
@@ -49,6 +60,34 @@ DEPS_SONAME=(
     "libgomp.so.1"
 )
 
+if [[ "$GPU_ARCH_TYPE" == "xpu" ]]; then
+    echo "Bundling with xpu support package libs."
+    DEPS_LIST+=(
+        "/opt/intel/oneapi/compiler/latest/lib/libsycl-preview.so.7"
+        "/opt/intel/oneapi/compiler/latest/lib/libOpenCL.so.1"
+        "/opt/intel/oneapi/compiler/latest/lib/libxptifw.so"
+        "/opt/intel/oneapi/compiler/latest/lib/libsvml.so"
+        "/opt/intel/oneapi/compiler/latest/lib/libirng.so"
+        "/opt/intel/oneapi/compiler/latest/lib/libimf.so"
+        "/opt/intel/oneapi/compiler/latest/lib/libintlc.so.5"
+        "/opt/intel/oneapi/compiler/latest/lib/libpi_level_zero.so"
+        "/opt/intel/oneapi/pti/latest/lib/libpti_view.so.0.9"
+        "/opt/intel/oneapi/pti/latest/lib/libpti.so.0.9"
+    )
+    DEPS_SONAME+=(
+        "libsycl-preview.so.7"
+        "libOpenCL.so.1"
+        "libxptifw.so"
+        "libsvml.so"
+        "libirng.so"
+        "libimf.so"
+        "libintlc.so.5"
+        "libpi_level_zero.so"
+        "libpti_view.so.0.9"
+        "libpti.so.0.9"
+    )
+fi
+
 rm -rf /usr/local/cuda*
 
 SOURCE_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null && pwd )"

.ci/manywheel/build_cuda.sh

@@ -59,19 +59,11 @@ cuda_version_nodot=$(echo $CUDA_VERSION | tr -d '.')
 
 TORCH_CUDA_ARCH_LIST="5.0;6.0;7.0;7.5;8.0;8.6"
 case ${CUDA_VERSION} in
-    12.6)
-        if [[ "$GPU_ARCH_TYPE" = "cuda-aarch64" ]]; then
-            TORCH_CUDA_ARCH_LIST="9.0"
-        else
-            TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST};9.0+PTX"
-        fi
-        EXTRA_CAFFE2_CMAKE_FLAGS+=("-DATEN_NO_TEST=ON")
-        ;;
     12.4)
         if [[ "$GPU_ARCH_TYPE" = "cuda-aarch64" ]]; then
             TORCH_CUDA_ARCH_LIST="9.0"
         else
-            TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST};9.0"
+            TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST};9.0+PTX"
         fi
         EXTRA_CAFFE2_CMAKE_FLAGS+=("-DATEN_NO_TEST=ON")
         ;;
@@ -83,6 +75,10 @@ case ${CUDA_VERSION} in
         TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST};3.7;9.0"
         EXTRA_CAFFE2_CMAKE_FLAGS+=("-DATEN_NO_TEST=ON")
         ;;
+    11.[67])
+        TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST};3.7"
+        EXTRA_CAFFE2_CMAKE_FLAGS+=("-DATEN_NO_TEST=ON")
+        ;;
     *)
         echo "unknown cuda version $CUDA_VERSION"
         exit 1
@@ -122,9 +118,7 @@ DEPS_SONAME=(
     "libgomp.so.1"
 )
 
-# CUDA 11.8 have to ship the libcusparseLt.so.0 with the binary
-# since nvidia-cusparselt-cu11 is not available in PYPI
-if [[ $USE_CUSPARSELT == "1" && $CUDA_VERSION == "11.8" ]]; then
+if [[ $USE_CUSPARSELT == "1" ]]; then
         DEPS_SONAME+=(
             "libcusparseLt.so.0"
         )
@@ -133,7 +127,7 @@ if [[ $USE_CUSPARSELT == "1" && $CUDA_VERSION == "11.8" ]]; then
         )
 fi
 
-if [[ $CUDA_VERSION == "12.4" || $CUDA_VERSION == "12.6" ]]; then
+if [[ $CUDA_VERSION == "12.1" || $CUDA_VERSION == "12.4" ]]; then
     export USE_STATIC_CUDNN=0
     # Try parallelizing nvcc as well
     export TORCH_NVCC_FLAGS="-Xfatbin -compress-all --threads 2"
@@ -151,7 +145,6 @@ if [[ $CUDA_VERSION == "12.4" || $CUDA_VERSION == "12.6" ]]; then
             "/usr/local/cuda/lib64/libcudnn.so.9"
             "/usr/local/cuda/lib64/libcublas.so.12"
             "/usr/local/cuda/lib64/libcublasLt.so.12"
-            "/usr/local/cuda/lib64/libcusparseLt.so.0"
             "/usr/local/cuda/lib64/libcudart.so.12"
             "/usr/local/cuda/lib64/libnvToolsExt.so.1"
             "/usr/local/cuda/lib64/libnvrtc.so.12"
@@ -168,7 +161,6 @@ if [[ $CUDA_VERSION == "12.4" || $CUDA_VERSION == "12.6" ]]; then
             "libcudnn.so.9"
             "libcublas.so.12"
             "libcublasLt.so.12"
-            "libcusparseLt.so.0"
             "libcudart.so.12"
             "libnvToolsExt.so.1"
             "libnvrtc.so.12"
@@ -186,7 +178,6 @@ if [[ $CUDA_VERSION == "12.4" || $CUDA_VERSION == "12.6" ]]; then
             '$ORIGIN/../../nvidia/curand/lib'
             '$ORIGIN/../../nvidia/cusolver/lib'
             '$ORIGIN/../../nvidia/cusparse/lib'
-            '$ORIGIN/../../cusparselt/lib'
             '$ORIGIN/../../nvidia/nccl/lib'
             '$ORIGIN/../../nvidia/nvtx/lib'
         )

.ci/manywheel/build_libtorch.sh

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

.ci/manywheel/build_rocm.sh

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

.ci/manywheel/build_xpu.sh

@@ -1,108 +0,0 @@
-#!/usr/bin/env bash
-
-set -ex
-
-export TH_BINARY_BUILD=1
-export USE_CUDA=0
-
-# Keep an array of cmake variables to add to
-if [[ -z "$CMAKE_ARGS" ]]; then
-    # These are passed to tools/build_pytorch_libs.sh::build()
-    CMAKE_ARGS=()
-fi
-if [[ -z "$EXTRA_CAFFE2_CMAKE_FLAGS" ]]; then
-    # These are passed to tools/build_pytorch_libs.sh::build_caffe2()
-    EXTRA_CAFFE2_CMAKE_FLAGS=()
-fi
-
-
-# Refer https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpus.html
-source /opt/intel/oneapi/compiler/latest/env/vars.sh
-source /opt/intel/oneapi/pti/latest/env/vars.sh
-source /opt/intel/oneapi/umf/latest/env/vars.sh
-export USE_STATIC_MKL=1
-
-WHEELHOUSE_DIR="wheelhousexpu"
-LIBTORCH_HOUSE_DIR="libtorch_housexpu"
-if [[ -z "$PYTORCH_FINAL_PACKAGE_DIR" ]]; then
-    if [[ -z "$BUILD_PYTHONLESS" ]]; then
-        PYTORCH_FINAL_PACKAGE_DIR="/remote/wheelhousexpu"
-    else
-        PYTORCH_FINAL_PACKAGE_DIR="/remote/libtorch_housexpu"
-    fi
-fi
-mkdir -p "$PYTORCH_FINAL_PACKAGE_DIR" || true
-
-OS_NAME=$(awk -F= '/^NAME/{print $2}' /etc/os-release)
-if [[ "$OS_NAME" == *"CentOS Linux"* ]]; then
-    LIBGOMP_PATH="/usr/lib64/libgomp.so.1"
-elif [[ "$OS_NAME" == *"Red Hat Enterprise Linux"* ]]; then
-    LIBGOMP_PATH="/usr/lib64/libgomp.so.1"
-elif [[ "$OS_NAME" == *"AlmaLinux"* ]]; then
-    LIBGOMP_PATH="/usr/lib64/libgomp.so.1"
-elif [[ "$OS_NAME" == *"Ubuntu"* ]]; then
-    if [[ "$(uname -m)" == "s390x" ]]; then
-        LIBGOMP_PATH="/usr/lib/s390x-linux-gnu/libgomp.so.1"
-    else
-        LIBGOMP_PATH="/usr/lib/x86_64-linux-gnu/libgomp.so.1"
-    fi
-fi
-
-DEPS_LIST=(
-    "$LIBGOMP_PATH"
-    "/opt/intel/oneapi/compiler/latest/lib/libOpenCL.so.1"
-)
-
-DEPS_SONAME=(
-    "libgomp.so.1"
-    "libOpenCL.so.1"
-)
-
-if [[ -z "$PYTORCH_EXTRA_INSTALL_REQUIREMENTS" ]]; then
-    echo "Bundling with xpu support package libs."
-    DEPS_LIST+=(
-        "/opt/intel/oneapi/compiler/latest/lib/libsycl.so.8"
-        "/opt/intel/oneapi/compiler/latest/lib/libur_loader.so.0"
-        "/opt/intel/oneapi/compiler/latest/lib/libur_adapter_level_zero.so.0"
-        "/opt/intel/oneapi/compiler/latest/lib/libur_adapter_opencl.so.0"
-        "/opt/intel/oneapi/compiler/latest/lib/libsvml.so"
-        "/opt/intel/oneapi/compiler/latest/lib/libirng.so"
-        "/opt/intel/oneapi/compiler/latest/lib/libimf.so"
-        "/opt/intel/oneapi/compiler/latest/lib/libintlc.so.5"
-        "/opt/intel/oneapi/pti/latest/lib/libpti_view.so.0.10"
-        "/opt/intel/oneapi/umf/latest/lib/libumf.so.0"
-        "/opt/intel/oneapi/tcm/latest/lib/libhwloc.so.15"
-    )
-    DEPS_SONAME+=(
-        "libsycl.so.8"
-        "libur_loader.so.0"
-        "libur_adapter_level_zero.so.0"
-        "libur_adapter_opencl.so.0"
-        "libsvml.so"
-        "libirng.so"
-        "libimf.so"
-        "libintlc.so.5"
-        "libpti_view.so.0.10"
-        "libumf.so.0"
-        "libhwloc.so.15"
-    )
-else
-    echo "Using xpu runtime libs from pypi."
-    XPU_RPATHS=(
-        '$ORIGIN/../../../..'
-    )
-    XPU_RPATHS=$(IFS=: ; echo "${XPU_RPATHS[*]}")
-    export C_SO_RPATH=$XPU_RPATHS':$ORIGIN:$ORIGIN/lib'
-    export LIB_SO_RPATH=$XPU_RPATHS':$ORIGIN'
-    export FORCE_RPATH="--force-rpath"
-fi
-
-rm -rf /usr/local/cuda*
-
-SOURCE_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null && pwd )"
-if [[ -z "$BUILD_PYTHONLESS" ]]; then
-    BUILD_SCRIPT=build_common.sh
-else
-    BUILD_SCRIPT=build_libtorch.sh
-fi
-source ${SOURCE_DIR}/${BUILD_SCRIPT}

.ci/manywheel/set_desired_python.sh

@@ -1,30 +0,0 @@
-#!/usr/bin/env bash
-
-# Require only one python installation
-if [[ -z "$DESIRED_PYTHON" ]]; then
-    echo "Need to set DESIRED_PYTHON env variable"
-    exit 1
-fi
-
-# If given a python version like 3.6m or 2.7mu, convert this to the format we
-# expect. The binary CI jobs pass in python versions like this; they also only
-# ever pass one python version, so we assume that DESIRED_PYTHON is not a list
-# in this case
-if [[ -n "$DESIRED_PYTHON" && $DESIRED_PYTHON =~ ([0-9].[0-9]+)t ]]; then
-    python_digits="$(echo $DESIRED_PYTHON | tr -cd [:digit:])"
-    py_majmin="${DESIRED_PYTHON}"
-    DESIRED_PYTHON="cp${python_digits}-cp${python_digits}t"
-elif [[ -n "$DESIRED_PYTHON" && "$DESIRED_PYTHON" != cp* ]]; then
-    python_nodot="$(echo $DESIRED_PYTHON | tr -d m.u)"
-    DESIRED_PYTHON="cp${python_nodot}-cp${python_nodot}"
-    if [[ ${python_nodot} -ge 310 ]]; then
-        py_majmin="${DESIRED_PYTHON:2:1}.${DESIRED_PYTHON:3:2}"
-    else
-        py_majmin="${DESIRED_PYTHON:2:1}.${DESIRED_PYTHON:3:1}"
-    fi
-fi
-
-pydir="/opt/python/$DESIRED_PYTHON"
-export DESIRED_PYTHON_BIN_DIR="${pydir}/bin"
-export PATH="$DESIRED_PYTHON_BIN_DIR:$PATH"
-echo "Will build for Python version: ${DESIRED_PYTHON}"

.ci/pytorch/build.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-set -ex -o pipefail
+set -ex
 
 # Required environment variable: $BUILD_ENVIRONMENT
 # (This is set by default in the Docker images we build, so you don't
@@ -87,7 +87,7 @@ else
 
   # Workaround required for MKL library linkage
   # https://github.com/pytorch/pytorch/issues/119557
-  if [[ "$ANACONDA_PYTHON_VERSION" = "3.12" || "$ANACONDA_PYTHON_VERSION" = "3.13" ]]; then
+  if [ "$ANACONDA_PYTHON_VERSION" = "3.12" ]; then
     export CMAKE_LIBRARY_PATH="/opt/conda/envs/py_$ANACONDA_PYTHON_VERSION/lib/"
     export CMAKE_INCLUDE_PATH="/opt/conda/envs/py_$ANACONDA_PYTHON_VERSION/include/"
   fi
@@ -191,7 +191,7 @@ fi
 
 # We only build FlashAttention files for CUDA 8.0+, and they require large amounts of
 # memory to build and will OOM
-if [[ "$BUILD_ENVIRONMENT" == *cuda* ]] && [[ 1 -eq $(echo "${TORCH_CUDA_ARCH_LIST} >= 8.0" | bc) ]]; then
+if [[ "$BUILD_ENVIRONMENT" == *cuda* ]] && [[ "$TORCH_CUDA_ARCH_LIST" == *"8.6"* || "$TORCH_CUDA_ARCH_LIST" == *"8.0"* ]]; then
   echo "WARNING: FlashAttention files require large amounts of memory to build and will OOM"
   echo "Setting MAX_JOBS=(nproc-2)/3 to reduce memory usage"
   export MAX_JOBS="$(( $(nproc --ignore=2) / 3 ))"
@@ -230,7 +230,7 @@ fi
 
 # Do not change workspace permissions for ROCm CI jobs
 # as it can leave workspace with bad permissions for cancelled jobs
-if [[ "$BUILD_ENVIRONMENT" != *rocm* && "$BUILD_ENVIRONMENT" != *s390x* && -d /var/lib/jenkins/workspace ]]; then
+if [[ "$BUILD_ENVIRONMENT" != *rocm* && "$BUILD_ENVIRONMENT" != *s390x* ]]; then
   # Workaround for dind-rootless userid mapping (https://github.com/pytorch/ci-infra/issues/96)
   WORKSPACE_ORIGINAL_OWNER_ID=$(stat -c '%u' "/var/lib/jenkins/workspace")
   cleanup_workspace() {
@@ -250,6 +250,7 @@ if [[ "$BUILD_ENVIRONMENT" == *-bazel-* ]]; then
   set -e
 
   get_bazel
+  install_sccache_nvcc_for_bazel
 
   # Leave 1 CPU free and use only up to 80% of memory to reduce the change of crashing
   # the runner
@@ -284,7 +285,8 @@ else
       WERROR=1 python setup.py clean
 
       if [[ "$USE_SPLIT_BUILD" == "true" ]]; then
-        python3 tools/packaging/split_wheel.py bdist_wheel
+        BUILD_LIBTORCH_WHL=1 BUILD_PYTHON_ONLY=0 python setup.py bdist_wheel
+        BUILD_LIBTORCH_WHL=0 BUILD_PYTHON_ONLY=1 python setup.py bdist_wheel --cmake
       else
         WERROR=1 python setup.py bdist_wheel
       fi
@@ -395,7 +397,7 @@ if [[ "$BUILD_ENVIRONMENT" != *libtorch* && "$BUILD_ENVIRONMENT" != *bazel* ]];
   # don't do this for libtorch as libtorch is C++ only and thus won't have python tests run on its build
   python tools/stats/export_test_times.py
 fi
-# don't do this for bazel or s390x as they don't use sccache
-if [[ "$BUILD_ENVIRONMENT" != *s390x* && "$BUILD_ENVIRONMENT" != *-bazel-* ]]; then
+
+if [[ "$BUILD_ENVIRONMENT" != *s390x* ]]; then
   print_sccache_stats
 fi

.ci/pytorch/common_utils.sh

@@ -81,15 +81,14 @@ function pip_install_whl() {
 
 function pip_install() {
   # retry 3 times
-  pip_install_pkg="python3 -m pip install --progress-bar off"
-  ${pip_install_pkg} "$@" || \
-    ${pip_install_pkg} "$@" || \
-    ${pip_install_pkg} "$@"
+  # old versions of pip don't have the "--progress-bar" flag
+  pip install --progress-bar off "$@" || pip install --progress-bar off "$@" || pip install --progress-bar off "$@" ||\
+  pip install "$@" || pip install "$@" || pip install "$@"
 }
 
 function pip_uninstall() {
   # uninstall 2 times
-  pip3 uninstall -y "$@" || pip3 uninstall -y "$@"
+  pip uninstall -y "$@" || pip uninstall -y "$@"
 }
 
 function get_exit_code() {
@@ -105,12 +104,32 @@ function get_bazel() {
   # version of Bazelisk to fetch the platform specific version of
   # Bazel to use from .bazelversion.
   retry curl --location --output tools/bazel \
-    https://raw.githubusercontent.com/bazelbuild/bazelisk/v1.23.0/bazelisk.py
+    https://raw.githubusercontent.com/bazelbuild/bazelisk/v1.16.0/bazelisk.py
   shasum --algorithm=1 --check \
-    <(echo '01df9cf7f08dd80d83979ed0d0666a99349ae93c  tools/bazel')
+    <(echo 'd4369c3d293814d3188019c9f7527a948972d9f8  tools/bazel')
   chmod u+x tools/bazel
 }
 
+# This function is bazel specific because of the bug
+# in the bazel that requires some special paths massaging
+# as a workaround. See
+# https://github.com/bazelbuild/bazel/issues/10167
+function install_sccache_nvcc_for_bazel() {
+  sudo mv /usr/local/cuda/bin/nvcc /usr/local/cuda/bin/nvcc-real
+
+  # Write the `/usr/local/cuda/bin/nvcc`
+  cat << EOF | sudo tee /usr/local/cuda/bin/nvcc
+#!/bin/sh
+if [ \$(env -u LD_PRELOAD ps -p \$PPID -o comm=) != sccache ]; then
+  exec sccache /usr/local/cuda/bin/nvcc "\$@"
+else
+  exec external/local_cuda/cuda/bin/nvcc-real "\$@"
+fi
+EOF
+
+  sudo chmod +x /usr/local/cuda/bin/nvcc
+}
+
 function install_monkeytype {
   # Install MonkeyType
   pip_install MonkeyType
@@ -221,12 +240,6 @@ function checkout_install_torchbench() {
   popd
 }
 
-function install_torchao() {
-  local commit
-  commit=$(get_pinned_commit torchao)
-  pip_install --no-use-pep517 --user "git+https://github.com/pytorch/ao.git@${commit}"
-}
-
 function print_sccache_stats() {
   echo 'PyTorch Build Statistics'
   sccache --show-stats

.ci/pytorch/macos-test.sh

@@ -1,5 +1,4 @@
 #!/bin/bash
-set -x
 
 # shellcheck disable=SC2034
 # shellcheck source=./macos-common.sh
@@ -149,146 +148,9 @@ test_jit_hooks() {
   assert_git_not_dirty
 }
 
-torchbench_setup_macos() {
-  git clone --recursive https://github.com/pytorch/vision torchvision
-  git clone --recursive https://github.com/pytorch/audio torchaudio
-
-  pushd torchvision
-  git fetch
-  git checkout "$(cat ../.github/ci_commit_pins/vision.txt)"
-  git submodule update --init --recursive
-  python setup.py clean
-  python setup.py develop
-  popd
-
-  pushd torchaudio
-  git fetch
-  git checkout "$(cat ../.github/ci_commit_pins/audio.txt)"
-  git submodule update --init --recursive
-  python setup.py clean
-  python setup.py develop
-  popd
-
-  # Shellcheck doesn't like it when you pass no arguments to a function that can take args. See https://www.shellcheck.net/wiki/SC2120
-  # shellcheck disable=SC2119,SC2120
-  checkout_install_torchbench
-}
-
-conda_benchmark_deps() {
-  conda install -y astunparse numpy scipy ninja pyyaml setuptools cmake typing-extensions requests protobuf numba cython scikit-learn
-  conda install -y -c conda-forge librosa
-}
-
-
-test_torchbench_perf() {
-  print_cmake_info
-
-  echo "Launching torchbench setup"
-  conda_benchmark_deps
-  torchbench_setup_macos
-
-  TEST_REPORTS_DIR=$(pwd)/test/test-reports
-  mkdir -p "$TEST_REPORTS_DIR"
-
-  local backend=eager
-  local dtype=notset
-  local device=mps
-
-  echo "Setup complete, launching torchbench training performance run"
-  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py \
-    --performance --backend "$backend" --training --devices "$device" \
-    --output "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_training_${device}_performance.csv"
-
-  echo "Launching torchbench inference performance run"
-  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py \
-    --performance --backend "$backend" --inference --devices "$device" \
-    --output "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_inference_${device}_performance.csv"
-
-  echo "Pytorch benchmark on mps device completed"
-}
-
-test_torchbench_smoketest() {
-  print_cmake_info
-
-  echo "Launching torchbench setup"
-  conda_benchmark_deps
-  # shellcheck disable=SC2119,SC2120
-  torchbench_setup_macos
-
-  TEST_REPORTS_DIR=$(pwd)/test/test-reports
-  mkdir -p "$TEST_REPORTS_DIR"
-
-  local backend=eager
-  local dtype=notset
-  local device=mps
-
-  touch "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_training_${device}_performance.csv"
-  touch "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_inference_${device}_performance.csv"
-
-  echo "Setup complete, launching torchbench training performance run"
-  for model in hf_T5 llama BERT_pytorch dcgan hf_GPT2 yolov3 resnet152; do
-    PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py \
-      --performance --only "$model" --backend "$backend" --training --devices "$device" \
-      --output "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_training_${device}_performance.csv"
-  done
-
-  echo "Launching torchbench inference performance run"
-  for model in hf_T5 llama BERT_pytorch dcgan hf_GPT2 yolov3 resnet152; do
-    PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py \
-      --performance --only "$model" --backend "$backend" --inference --devices "$device" \
-      --output "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_inference_${device}_performance.csv"
-  done
-
-  echo "Pytorch benchmark on mps device completed"
-}
-
-test_hf_perf() {
-  print_cmake_info
-  TEST_REPORTS_DIR=$(pwd)/test/test-reports
-  mkdir -p "$TEST_REPORTS_DIR"
-  conda_benchmark_deps
-  torchbench_setup_macos
-
-  echo "Launching HuggingFace training perf run"
-  python "$(pwd)"/benchmarks/dynamo/huggingface.py --backend eager --device mps --performance --training --output="${TEST_REPORTS_DIR}"/hf_training.csv
-
-  echo "Launching HuggingFace inference perf run"
-  python "$(pwd)"/benchmarks/dynamo/huggingface.py --backend eager --device mps --performance --training --output="${TEST_REPORTS_DIR}"/hf_inference.csv
-
-  echo "HuggingFace benchmark on mps device completed"
-}
-
-test_timm_perf() {
-  print_cmake_info
-  TEST_REPORTS_DIR=$(pwd)/test/test-reports
-  mkdir -p "$TEST_REPORTS_DIR"
-  conda_benchmark_deps
-  torchbench_setup_macos
-
-  echo "Launching timm training perf run"
-  python "$(pwd)"/benchmarks/dynamo/timm_models.py --backend eager --device mps --performance --training --output="${TEST_REPORTS_DIR}"/timm_training.csv
-
-  echo "Launching timm inference perf run"
-  python "$(pwd)"/benchmarks/dynamo/timm_models.py --backend eager --device mps --performance --training --output="${TEST_REPORTS_DIR}"/timm_inference.csv
-
-  echo "timm benchmark on mps device completed"
-}
-
 install_tlparse
 
-if [[ $TEST_CONFIG == *"perf_all"* ]]; then
-  test_torchbench_perf
-  test_hf_perf
-  test_timm_perf
-elif [[ $TEST_CONFIG == *"perf_torchbench"* ]]; then
-  test_torchbench_perf
-elif [[ $TEST_CONFIG == *"perf_hf"* ]]; then
-  test_hf_perf
-elif [[ $TEST_CONFIG == *"perf_timm"* ]]; then
-  test_timm_perf
-elif [[ $TEST_CONFIG == *"perf_smoketest"* ]]; then
-  test_torchbench_smoketest
-elif [[ $NUM_TEST_SHARDS -gt 1 ]]; then
+if [[ $NUM_TEST_SHARDS -gt 1 ]]; then
   test_python_shard "${SHARD_NUMBER}"
   if [[ "${SHARD_NUMBER}" == 1 ]]; then
     test_libtorch

.ci/pytorch/test.sh

@@ -14,7 +14,7 @@ source "$(dirname "${BASH_SOURCE[0]}")/common.sh"
 
 # Do not change workspace permissions for ROCm CI jobs
 # as it can leave workspace with bad permissions for cancelled jobs
-if [[ "$BUILD_ENVIRONMENT" != *rocm* && -d /var/lib/jenkins/workspace ]]; then
+if [[ "$BUILD_ENVIRONMENT" != *rocm* ]]; then
   # Workaround for dind-rootless userid mapping (https://github.com/pytorch/ci-infra/issues/96)
   WORKSPACE_ORIGINAL_OWNER_ID=$(stat -c '%u' "/var/lib/jenkins/workspace")
   cleanup_workspace() {
@@ -48,7 +48,7 @@ NUM_TEST_SHARDS="${NUM_TEST_SHARDS:=1}"
 
 export VALGRIND=ON
 # export TORCH_INDUCTOR_INSTALL_GXX=ON
-if [[ "$BUILD_ENVIRONMENT" == *clang9* || "$BUILD_ENVIRONMENT" == *xpu* ]]; then
+if [[ "$BUILD_ENVIRONMENT" == *clang9* ]]; then
   # clang9 appears to miscompile code involving std::optional<c10::SymInt>,
   # such that valgrind complains along these lines:
   #
@@ -169,13 +169,9 @@ fi
 
 if [[ "$BUILD_ENVIRONMENT" == *xpu* ]]; then
   # Source Intel oneAPI envrioment script to enable xpu runtime related libraries
-  # refer to https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpus.html
+  # refer to https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpu/2-5.html
   # shellcheck disable=SC1091
   source /opt/intel/oneapi/compiler/latest/env/vars.sh
-  if [ -f /opt/intel/oneapi/umf/latest/env/vars.sh ]; then
-    # shellcheck disable=SC1091
-    source /opt/intel/oneapi/umf/latest/env/vars.sh
-  fi
   # Check XPU status before testing
   xpu-smi discovery
 fi
@@ -615,11 +611,6 @@ test_single_dynamo_benchmark() {
 }
 
 test_inductor_micro_benchmark() {
-  # torchao requires cuda 8.0 or above for bfloat16 support
-  if [[ "$BUILD_ENVIRONMENT" == *cuda* ]]; then
-    export TORCH_CUDA_ARCH_LIST="8.0;8.6"
-  fi
-  install_torchao
   TEST_REPORTS_DIR=$(pwd)/test/test-reports
   if [[ "${TEST_CONFIG}" == *cpu* ]]; then
     test_inductor_set_cpu_affinity
@@ -957,9 +948,6 @@ test_distributed() {
     python test/run_test.py --cpp --verbose -i cpp/HashStoreTest
     python test/run_test.py --cpp --verbose -i cpp/TCPStoreTest
 
-    echo "Testing multi-GPU linalg tests"
-    python test/run_test.py -i test_linalg.py -k test_matmul_offline_mgpu_tunable --verbose
-
     if [[ "$BUILD_ENVIRONMENT" == *cuda* ]]; then
       MPIEXEC=$(command -v mpiexec)
       if [[ -n "$MPIEXEC" ]]; then
@@ -1209,7 +1197,7 @@ EOF
   git reset --hard "${SHA_TO_COMPARE}"
   git submodule sync && git submodule update --init --recursive
   echo "::group::Installing Torch From Base Commit"
-  pip3 install -r requirements.txt
+  pip install -r requirements.txt
   # shellcheck source=./common-build.sh
   source "$(dirname "${BASH_SOURCE[0]}")/common-build.sh"
   python setup.py bdist_wheel --bdist-dir="base_bdist_tmp" --dist-dir="base_dist"
@@ -1366,11 +1354,10 @@ test_executorch() {
   export EXECUTORCH_BUILD_PYBIND=ON
   export CMAKE_ARGS="-DEXECUTORCH_BUILD_XNNPACK=ON -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON"
 
-  # For llama3
-  bash examples/models/llama3_2_vision/install_requirements.sh
   # NB: We need to rebuild ExecuTorch runner here because it depends on PyTorch
   # from the PR
-  bash .ci/scripts/setup-linux.sh cmake
+  # shellcheck disable=SC1091
+  source .ci/scripts/setup-linux.sh cmake
 
   echo "Run ExecuTorch unit tests"
   pytest -v -n auto
@@ -1393,8 +1380,7 @@ test_executorch() {
 
 test_linux_aarch64() {
   python test/run_test.py --include test_modules test_mkldnn test_mkldnn_fusion test_openmp test_torch test_dynamic_shapes \
-        test_transformers test_multiprocessing test_numpy_interop test_autograd test_binary_ufuncs test_complex test_spectral_ops \
-        test_foreach test_reductions test_unary_ufuncs \
+        test_transformers test_multiprocessing test_numpy_interop \
         --shard "$SHARD_NUMBER" "$NUM_TEST_SHARDS" --verbose
 
   # Dynamo tests
@@ -1412,7 +1398,6 @@ test_linux_aarch64() {
        inductor/test_pattern_matcher inductor/test_perf inductor/test_profiler inductor/test_select_algorithm inductor/test_smoke \
        inductor/test_split_cat_fx_passes inductor/test_standalone_compile inductor/test_torchinductor \
        inductor/test_torchinductor_codegen_dynamic_shapes inductor/test_torchinductor_dynamic_shapes inductor/test_memory \
-       inductor/test_triton_cpu_backend inductor/test_triton_extension_backend inductor/test_mkldnn_pattern_matcher inductor/test_cpu_cpp_wrapper \
        --shard "$SHARD_NUMBER" "$NUM_TEST_SHARDS" --verbose
 }
 
@@ -1420,11 +1405,7 @@ if ! [[ "${BUILD_ENVIRONMENT}" == *libtorch* || "${BUILD_ENVIRONMENT}" == *-baze
   (cd test && python -c "import torch; print(torch.__config__.show())")
   (cd test && python -c "import torch; print(torch.__config__.parallel_info())")
 fi
-if [[ "${TEST_CONFIG}" == *numpy_2* ]]; then
-  # Install numpy-2.0.2 and compatible scipy & numba versions
-  python -mpip install --pre numpy==2.0.2 scipy==1.13.1 numba==0.60.0
-  python test/run_test.py --include dynamo/test_functions.py dynamo/test_unspec.py test_binary_ufuncs.py test_fake_tensor.py test_linalg.py test_numpy_interop.py test_tensor_creation_ops.py test_torch.py torch_np/test_basic.py
-elif [[ "${BUILD_ENVIRONMENT}" == *aarch64* && "${TEST_CONFIG}" != *perf_cpu_aarch64* ]]; then
+if [[ "${BUILD_ENVIRONMENT}" == *aarch64* && "${TEST_CONFIG}" != *perf_cpu_aarch64* ]]; then
   test_linux_aarch64
 elif [[ "${TEST_CONFIG}" == *backward* ]]; then
   test_forward_backward_compatibility

.ci/pytorch/test_example_code/CMakeLists.txt

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

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

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

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

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

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

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

.ci/pytorch/test_example_code/cnn_smoke.py

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

.ci/pytorch/test_example_code/rnn_smoke.py

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

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

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

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

@@ -1,6 +1,6 @@
 @echo on
 REM Description: Install Intel Support Packages on Windows
-REM BKM reference: https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpus.html
+REM BKM reference: https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpu/2-5.html
 
 set XPU_INSTALL_MODE=%~1
 if "%XPU_INSTALL_MODE%"=="" goto xpu_bundle_install_start
@@ -28,28 +28,15 @@ if "%XPU_INSTALL_MODE%"=="driver" goto xpu_install_end
 
 set XPU_BUNDLE_PARENT_DIR=C:\Program Files (x86)\Intel\oneAPI
 set XPU_BUNDLE_URL=https://registrationcenter-download.intel.com/akdlm/IRC_NAS/9d1a91e2-e8b8-40a5-8c7f-5db768a6a60c/w_intel-for-pytorch-gpu-dev_p_0.5.3.37_offline.exe
-set XPU_BUNDLE_PRODUCT_NAME=intel.oneapi.win.intel-for-pytorch-gpu-dev.product
+set XPU_PTI_URL=https://registrationcenter-download.intel.com/akdlm/IRC_NAS/9d1a91e2-e8b8-40a5-8c7f-5db768a6a60c/w_intel-pti-dev_p_0.9.0.37_offline.exe
 set XPU_BUNDLE_VERSION=0.5.3+31
+set XPU_PTI_VERSION=0.9.0+36
+set XPU_BUNDLE_PRODUCT_NAME=intel.oneapi.win.intel-for-pytorch-gpu-dev.product
+set XPU_PTI_PRODUCT_NAME=intel.oneapi.win.intel-pti-dev.product
 set XPU_BUNDLE_INSTALLED=0
+set XPU_PTI_INSTALLED=0
 set XPU_BUNDLE_UNINSTALL=0
-set XPU_EXTRA_URL=https://registrationcenter-download.intel.com/akdlm/IRC_NAS/9d1a91e2-e8b8-40a5-8c7f-5db768a6a60c/w_intel-pti-dev_p_0.9.0.37_offline.exe
-set XPU_EXTRA_PRODUCT_NAME=intel.oneapi.win.intel-pti-dev.product
-set XPU_EXTRA_VERSION=0.9.0+36
-set XPU_EXTRA_INSTALLED=0
-set XPU_EXTRA_UNINSTALL=0
-
-if not [%XPU_VERSION%]==[] if [%XPU_VERSION%]==[2025.0] (
-    set XPU_BUNDLE_URL=https://registrationcenter-download.intel.com/akdlm/IRC_NAS/efc86abd-cb77-452e-a03f-a741895b8ece/intel-deep-learning-essentials-2025.0.0.336_offline.exe
-    set XPU_BUNDLE_PRODUCT_NAME=intel.oneapi.win.deep-learning-essentials.product
-    set XPU_BUNDLE_VERSION=2025.0.0+335
-    set XPU_BUNDLE_INSTALLED=0
-    set XPU_BUNDLE_UNINSTALL=0
-    set XPU_EXTRA_URL=NULL
-    set XPU_EXTRA_PRODUCT_NAME=intel.oneapi.win.compiler.product
-    set XPU_EXTRA_VERSION=2025.0.1+1226
-    set XPU_EXTRA_INSTALLED=0
-    set XPU_EXTRA_UNINSTALL=0
-)
+set XPU_PTI_UNINSTALL=0
 
 :: Check if XPU bundle is target version or already installed
 if exist "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" goto xpu_bundle_ver_check
@@ -64,34 +51,25 @@ for /f "tokens=1,2" %%a in (xpu_bundle_installed_ver.log) do (
         echo %%a Installed Version: %%b
         set XPU_BUNDLE_INSTALLED=1
         if not "%XPU_BUNDLE_VERSION%"=="%%b" (
-            start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %%a --product-ver %%b --log-dir uninstall_bundle
+            start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %XPU_BUNDLE_PRODUCT_NAME% --product-ver %%b --log-dir uninstall_bundle
             set XPU_BUNDLE_UNINSTALL=1
         )
     )
-    if "%%a"=="%XPU_EXTRA_PRODUCT_NAME%" (
+    if "%%a"=="%XPU_PTI_PRODUCT_NAME%" (
         echo %%a Installed Version: %%b
-        set XPU_EXTRA_INSTALLED=1
-        if not "%XPU_EXTRA_VERSION%"=="%%b" (
-            start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %%a --product-ver %%b --log-dir uninstall_bundle
-            set XPU_EXTRA_UNINSTALL=1
+        set XPU_PTI_INSTALLED=1
+        if not "%XPU_PTI_VERSION%"=="%%b" (
+            start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %XPU_PTI_PRODUCT_NAME% --product-ver %%b --log-dir uninstall_bundle
+            set XPU_PTI_UNINSTALL=1
         )
     )
-    if not "%%b" == "Version" if not [%%b]==[] if not "%%a"=="%XPU_BUNDLE_PRODUCT_NAME%" if not "%%a"=="%XPU_EXTRA_PRODUCT_NAME%" (
-        echo "Uninstalling...."
-        start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %%a --product-ver %%b --log-dir uninstall_bundle
-    )
 )
 if errorlevel 1 exit /b 1
 if exist xpu_bundle_installed_ver.log del xpu_bundle_installed_ver.log
-if exist uninstall_bundle rmdir /s /q uninstall_bundle
 if "%XPU_BUNDLE_INSTALLED%"=="0" goto xpu_bundle_install
 if "%XPU_BUNDLE_UNINSTALL%"=="1" goto xpu_bundle_install
-
-:xpu_extra_check
-
-if "%XPU_EXTRA_URL%"=="NULL" goto xpu_install_end
-if "%XPU_EXTRA_INSTALLED%"=="0" goto xpu_extra_install
-if "%XPU_EXTRA_UNINSTALL%"=="1" goto xpu_extra_install
+if "%XPU_PTI_INSTALLED%"=="0" goto xpu_pti_install
+if "%XPU_PTI_UNINSTALL%"=="1" goto xpu_pti_install
 goto xpu_install_end
 
 :xpu_bundle_install
@@ -101,14 +79,13 @@ echo "XPU Bundle installing..."
 start /wait "Intel Pytorch Bundle Installer" "xpu_bundle.exe" --action=install --eula=accept --silent --log-dir install_bundle
 if errorlevel 1 exit /b 1
 del xpu_bundle.exe
-goto xpu_extra_check
 
-:xpu_extra_install
+:xpu_pti_install
 
-curl -o xpu_extra.exe --retry 3 --retry-all-errors -k %XPU_EXTRA_URL%
-echo "Intel XPU EXTRA installing..."
-start /wait "Intel XPU EXTRA Installer" "xpu_extra.exe" --action=install --eula=accept --silent --log-dir install_bundle
+curl -o xpu_pti.exe --retry 3 --retry-all-errors -k %XPU_PTI_URL%
+echo "XPU PTI installing..."
+start /wait "Intel PTI Installer" "xpu_pti.exe" --action=install --eula=accept --silent --log-dir install_bundle
 if errorlevel 1 exit /b 1
-del xpu_extra.exe
+del xpu_pti.exe
 
 :xpu_install_end

.ci/pytorch/win-test.sh

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

.ci/pytorch/windows/build_pytorch.bat

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

.ci/pytorch/windows/condaenv.bat

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

.ci/pytorch/windows/cpu.bat

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

.ci/pytorch/windows/cuda118.bat

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

.ci/pytorch/windows/cuda124.bat

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

.ci/pytorch/windows/cuda126.bat

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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