mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-06-13 01:09:22 +00:00
### Description This PR is to update the win-ort-main branch to the tip main branch as of 2025-01-23. ### PR List ddf0d377a7 [QNN EP] Add LoggingManager::HasDefaultLogger() to provider bridge API (#23467) 05fbbdf91f [QNN EP] Make QNN EP a shared library (#23120) 1336566d7f Add custom vcpkg ports (#23456) 2e1173c411 Update the compile flags for vcpkg packages (#23455) 1f628a9858 [Mobile] Add BrowserStack Android MAUI Test (#23383) 009cae0ec8 [js/webgpu] Optimize ConvTranspose (Continue) (#23429) 04a4a694cb Use onnx_protobuf.h to suppress some GCC warnings (#23453) 2e3b62b4b0 Suppress some strict-aliasing related warnings in WebGPU EP (#23454) b708f9b1dc Bump ruff from 0.9.1 to 0.9.2 (#23427) c0afc66b2a [WebNN] Remove workarounds for TFLite backend (#23406) 8a821ff7f9 Bump vite from 6.0.7 to 6.0.11 in /js/web/test/e2e/exports/testcases/vite-default (#23446) 220c1a203e Make ORT and Dawn use the same protobuf/abseil source code (#23447) b7b5792147 Change MacOS-13 to ubuntu on for android-java-api-aar-test.yml. (#23444) 19d0d2a30f WIP: Dp4MatMulNBits accuracy level 4 matmul for WebGPU EP (#23365) 95b8effbc4 [QNN EP]: Clean up QNN logging resources if an error occurs during initialization (#23435) 626134c5b5 Bump clang-format from 19.1.6 to 19.1.7 (#23428) 0cf975301f Fix eigen external deps (#23439) f9440aedce Moving RN_CI Android Testing to Linux (#23422) 1aa5902ff4 [QNN EP] workaround for QNN validation bug for Tanh with uint16 quantized output (#23432) 7f5582a0e2 Seperate RN andriod and IOS into 2 separated Stages. (#23400) 73deac2e7f Implement some missing element wise Add/Sub/Mul/Div/Neg operations for CPU and CUDA EPs (#23090) 949fe42af4 Upgrade Java version from react-native/android to Java 17 (#23066) 0892c23463 Update Qnn SDK default version to 2.30 (#23411) 94c099bcec Fix type cast build error (#23423) d633e571d1 [WebNN EP] Fix AddInitializersToSkip issues (#23354) e988ef00e2 [QNN EP] Fix regression for MatMul with two quantized/dynamic uint16 inputs (#23419) 7538795f6b Update onnxruntime binary size checks ci pipeline's docker image (#23405) 6c5ea41cad Revert "[QNN EP] Clean up correctly from a partial setup (#23320)" (#23420) e866804bbe Enable comprehension simplification in ruff rules (#23414) 0a5f1f392c bugfix: string_view of invalid memory (#23417) 4cc38e0277 fix crash when first input of BatchNormalization is 1-D (#23387) 033441487f Target py310 and modernize codebase with ruff (#23401) 87341ac010 [QNN EP] Fix segfault when unregistering HTP shared memory handles (#23402) ### Motivation and Context This update includes the change to make QNN-EP a shared library. --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Adrian Lizarraga <adlizarraga@microsoft.com> Co-authored-by: Justin Chu <justinchuby@users.noreply.github.com> Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Changming Sun <chasun@microsoft.com> Co-authored-by: Peishen Yan <peishen.yan@intel.com> Co-authored-by: Tianlei Wu <tlwu@microsoft.com> Co-authored-by: Hector Li <hecli@microsoft.com> Co-authored-by: Jian Chen <cjian@microsoft.com> Co-authored-by: Alexis Tsogias <1114095+Zyrin@users.noreply.github.com> Co-authored-by: junchao-zhao <68935141+junchao-loongson@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: sushraja-msft <44513542+sushraja-msft@users.noreply.github.com> Co-authored-by: Wanming Lin <wanming.lin@intel.com> Co-authored-by: Jiajia Qin <jiajiaqin@microsoft.com> Co-authored-by: Caroline Zhu <wolfivyaura@gmail.com>
97 lines
3 KiB
Bash
Executable file
97 lines
3 KiB
Bash
Executable file
#!/bin/bash
|
|
set -e -x
|
|
|
|
# This script invokes build.py
|
|
|
|
mkdir -p /build/dist
|
|
|
|
EXTRA_ARG=""
|
|
ENABLE_CACHE=false
|
|
# Put 3.10 at the last because Ubuntu 22.04 use python 3.10 and we will upload the intermediate build files of this
|
|
# config to Azure DevOps Artifacts and download them to a Ubuntu 22.04 machine to run the tests.
|
|
PYTHON_EXES=(
|
|
"/opt/python/cp311-cp311/bin/python3.11"
|
|
"/opt/python/cp312-cp312/bin/python3.12"
|
|
"/opt/python/cp313-cp313/bin/python3.13"
|
|
"/opt/python/cp313-cp313t/bin/python3.13t"
|
|
"/opt/python/cp310-cp310/bin/python3.10"
|
|
)
|
|
while getopts "d:p:x:c:e" parameter_Option
|
|
do case "${parameter_Option}"
|
|
in
|
|
#GPU|CPU|NPU.
|
|
d) BUILD_DEVICE=${OPTARG};;
|
|
p)
|
|
# Check if OPTARG is empty or starts with a hyphen, indicating a missing or invalid argument for -p
|
|
if [[ -z "${OPTARG}" || "${OPTARG}" == -* ]]; then
|
|
echo "ERROR: Option -p requires a valid argument, not another option."
|
|
exit 1
|
|
else
|
|
PYTHON_EXES=("${OPTARG}") # Use the provided argument for -p
|
|
fi
|
|
;;
|
|
x) EXTRA_ARG=${OPTARG};;
|
|
c) BUILD_CONFIG=${OPTARG};;
|
|
e) ENABLE_CACHE=true;;
|
|
*) echo "Usage: $0 -d <GPU|CPU|NPU> [-p <python_exe_path>] [-x <extra_build_arg>] [-c <build_config>]"
|
|
exit 1;;
|
|
esac
|
|
done
|
|
|
|
|
|
|
|
BUILD_ARGS=("--build_dir" "/build" "--config" "$BUILD_CONFIG" "--update" "--build" "--skip_submodule_sync" "--parallel" "--use_binskim_compliant_compile_flags" "--build_wheel")
|
|
|
|
if [ "$BUILD_CONFIG" != "Debug" ]; then
|
|
BUILD_ARGS+=("--enable_lto")
|
|
fi
|
|
if [ "$ENABLE_CACHE" = true ] ; then
|
|
BUILD_ARGS+=("--use_cache")
|
|
ccache -s;
|
|
fi
|
|
|
|
ARCH=$(uname -m)
|
|
|
|
|
|
|
|
|
|
echo "EXTRA_ARG:"
|
|
echo "$EXTRA_ARG"
|
|
|
|
if [ "$EXTRA_ARG" != "" ]; then
|
|
BUILD_ARGS+=("$EXTRA_ARG")
|
|
fi
|
|
|
|
if [ "$ARCH" == "x86_64" ]; then
|
|
#ARM build machines do not have the test data yet.
|
|
BUILD_ARGS+=("--enable_onnx_tests")
|
|
fi
|
|
|
|
if [ "$BUILD_DEVICE" == "GPU" ]; then
|
|
SHORT_CUDA_VERSION=$(echo $CUDA_VERSION | sed 's/\([[:digit:]]\+\.[[:digit:]]\+\)\.[[:digit:]]\+/\1/')
|
|
#Enable CUDA and TRT EPs.
|
|
BUILD_ARGS+=("--use_cuda" "--use_tensorrt" "--cuda_version=$SHORT_CUDA_VERSION" "--tensorrt_home=/usr" "--cuda_home=/usr/local/cuda-$SHORT_CUDA_VERSION" "--cudnn_home=/usr/local/cuda-$SHORT_CUDA_VERSION" "--cmake_extra_defines" "CMAKE_CUDA_ARCHITECTURES=75;80;90")
|
|
fi
|
|
|
|
if [ "$BUILD_DEVICE" == "NPU" ]; then
|
|
#Enable QNN EP
|
|
BUILD_ARGS+=("--build_shared_lib" "--use_qnn" "--qnn_home=/qnn_sdk")
|
|
fi
|
|
|
|
export ONNX_ML=1
|
|
export CMAKE_ARGS="-DONNX_GEN_PB_TYPE_STUBS=ON -DONNX_WERROR=OFF"
|
|
|
|
for PYTHON_EXE in "${PYTHON_EXES[@]}"
|
|
do
|
|
rm -rf /build/"$BUILD_CONFIG"
|
|
# that's a workaround for the issue that there's no python3 in the docker image
|
|
# like xnnpack's cmakefile, it uses pythone3 to run a external command
|
|
python3_dir=$(dirname "$PYTHON_EXE")
|
|
${PYTHON_EXE} -m pip install -r /onnxruntime_src/tools/ci_build/github/linux/python/requirements.txt
|
|
PATH=$python3_dir:$PATH ${PYTHON_EXE} /onnxruntime_src/tools/ci_build/build.py "${BUILD_ARGS[@]}"
|
|
cp /build/"$BUILD_CONFIG"/dist/*.whl /build/dist
|
|
done
|
|
|
|
if [ "$ENABLE_CACHE" = true ] ; then
|
|
which ccache && ccache -sv && ccache -z
|
|
fi
|