Build ONNX Runtime with Execution Providers

Execution Provider Shared Libraries
CUDA
TensorRT
NVIDIA Jetson TX1/TX2/Nano/Xavier/Orin
oneDNN
OpenVINO
QNN
DirectML
Arm Compute Library
Arm NN
RKNPU
AMD Vitis AI
AMD MIGraphX
AMD ROCm
NNAPI
CoreML
XNNPACK
CANN
Azure

Execution Provider Shared Libraries

The oneDNN, TensorRT, OpenVINO™, and CANN providers are built as shared libraries vs being statically linked into the main onnxruntime. This enables them to be loaded only when needed, and if the dependent libraries of the provider are not installed onnxruntime will still run fine, it just will not be able to use that provider. For non shared library providers, all dependencies of the provider must exist to load onnxruntime.

Built files

On Windows, shared provider libraries will be named ‘onnxruntime_providers_*.dll’ (for example onnxruntime_providers_openvino.dll). On Unix, they will be named ‘libonnxruntime_providers_*.so’ On Mac, they will be named ‘libonnxruntime_providers_*.dylib’.

There is also a shared library that shared providers depend on called onnxruntime_providers_shared (with the same naming convension applied as above).

Note: It is not recommended to put these libraries in a system location or added to a library search path (like LD_LIBRARY_PATH on Unix). If multiple versions of onnxruntime are installed on the system this can make them find the wrong libraries and lead to undefined behavior.

Loading the shared providers

Shared provider libraries are loaded by the onnxruntime code (do not load or depend on them in your client code). The API for registering shared or non shared providers is identical, the difference is that shared ones will be loaded at runtime when the provider is added to the session options (through a call like OrtSessionOptionsAppendExecutionProvider_OpenVINO or SessionOptionsAppendExecutionProvider_OpenVINO in the C API). If a shared provider library cannot be loaded (if the file doesn’t exist, or its dependencies don’t exist or not in the path) then an error will be returned.

The onnxruntime code will look for the provider shared libraries in the same location as the onnxruntime shared library is (or the executable statically linked to the static library version).

CUDA

Prerequisites

Install CUDA and cuDNN
- The CUDA execution provider for ONNX Runtime is built and tested with CUDA 11.8, 12.2 and cuDNN 8.9. Check here for more version information.
- The path to the CUDA installation must be provided via the CUDA_HOME environment variable, or the --cuda_home parameter. The installation directory should contain bin, include and lib sub-directories.
- The path to the CUDA bin directory must be added to the PATH environment variable so that nvcc is found.
- The path to the cuDNN installation must be provided via the CUDNN_HOME environment variable, or --cudnn_home parameter. In Windows, the installation directory should contain bin, include and lib sub-directories.
- cuDNN 8.* requires ZLib. Follow the cuDNN 8.9 installation guide to install zlib in Linux or Windows.
- In Windows, the path to the cuDNN bin directory must be added to the PATH environment variable so that cudnn64_8.dll is found.

Build Instructions

Windows

.\build.bat --use_cuda --cudnn_home <cudnn home path> --cuda_home <cuda home path>

Linux

./build.sh --use_cuda --cudnn_home <cudnn home path> --cuda_home <cuda home path>

A Dockerfile is available here.

Build Options

To specify GPU architectures (see Compute Capability), you can append parameters like --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=80;86;89.

With --cmake_extra_defines onnxruntime_USE_CUDA_NHWC_OPS=ON, the CUDA EP can be compiled with additional NHWC ops. This option is not enabled by default due to the small amount of supported NHWC operators.

Another very helpful CMake build option is to build with NVTX support (--cmake_extra_defines onnxruntime_ENABLE_NVTX_PROFILE=ON) that will enable much easier profiling using Nsight Systems and correlates CUDA kernels with their actual ONNX operator.

--enable_cuda_line_info or --cmake_extra_defines onnxruntime_ENABLE_CUDA_LINE_NUMBER_INFO=ON will enable NVCC generation of line-number information for device code. It might be helpful when you run Compute Sanitizer tools on CUDA kernels.

If your Windows machine has multiple versions of CUDA installed and you want to use an older version of CUDA, you need append parameters like --cuda_version <cuda version>.

When your build machine has many CPU cores and less than 64 GB memory, there is chance of out of memory error like nvcc error : 'cicc' died due to signal 9. The solution is to limit number of parallel NVCC threads with parameters like --parallel 4 --nvcc_threads 1.

Notes on older versions of ONNX Runtime, CUDA and Visual Studio

Depending on compatibility between the CUDA, cuDNN, and Visual Studio versions you are using, you may need to explicitly install an earlier version of the MSVC toolset.
For older version of ONNX Runtime and CUDA, and Visual Studio:
- CUDA 10.0 is known to work with toolsets from 14.11 up to 14.16 (Visual Studio 2017 15.9), and should continue to work with future Visual Studio versions
- CUDA 9.2 is known to work with the 14.11 MSVC toolset (Visual Studio 15.3 and 15.4)
  - To install the 14.11 MSVC toolset, see this page.
  - To use the 14.11 toolset with a later version of Visual Studio 2017 you have two options:
    1. Setup the Visual Studio environment variables to point to the 14.11 toolset by running vcvarsall.bat, prior to running the build script. e.g. if you have VS2017 Enterprise, an x64 build would use the following command "C:\Program Files (x86)\Microsoft Visual Studio\2017\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" amd64 -vcvars_ver=14.11 For convenience, .\build.amd64.1411.bat will do this and can be used in the same way as .\build.bat. e.g. ` .\build.amd64.1411.bat –use_cuda`
    2. Alternatively, if you have CMake 3.13 or later you can specify the toolset version via the --msvc_toolset build script parameter. e.g. .\build.bat --msvc_toolset 14.11
If you have multiple versions of CUDA installed on a Windows machine and are building with Visual Studio, CMake will use the build files for the highest version of CUDA it finds in the BuildCustomization folder. e.g. C:\Program Files (x86)\Microsoft Visual Studio\2017\Enterprise\Common7\IDE\VC\VCTargets\BuildCustomizations. If you want to build with an earlier version, you must temporarily remove the ‘CUDA x.y.*’ files for later versions from this directory.

TensorRT

See more information on the TensorRT Execution Provider here.

Prerequisites

Follow instructions for CUDA execution provider to install CUDA and cuDNN, and setup environment variables.
Follow instructions for installing TensorRT
- The TensorRT execution provider for ONNX Runtime is built and tested with TensorRT 10.0.
- The path to TensorRT installation must be provided via the --tensorrt_home parameter.
- ONNX Runtime uses TensorRT built-in parser from tensorrt_home by default.
- To use open-sourced onnx-tensorrt parser instead, add --use_tensorrt_oss_parser parameter in build commands below.
  - The default version of open-sourced onnx-tensorrt parser is encoded in cmake/deps.txt.
  - To specify a different version of onnx-tensorrt parser:
    - Select the commit of onnx-tensorrt that you preferred;
    - Run sha1sum command with downloaded onnx-tensorrt zip file to acquire the SHA1 hash
    - Update cmake/deps.txt with updated onnx-tensorrt commit and hash info.

Build Instructions

Windows

# to build with tensorrt built-in parser
.\build.bat --cudnn_home <path to cuDNN home> --cuda_home <path to CUDA home> --use_tensorrt --tensorrt_home <path to TensorRT home> --cmake_generator "Visual Studio 17 2022"

# to build with specific version of open-sourced onnx-tensorrt parser configured in cmake/deps.txt
.\build.bat --cudnn_home <path to cuDNN home> --cuda_home <path to CUDA home> --use_tensorrt --tensorrt_home <path to TensorRT home> --use_tensorrt_oss_parser --cmake_generator "Visual Studio 17 2022" 

Linux

# to build with tensorrt built-in parser
./build.sh --cudnn_home <path to cuDNN e.g. /usr/lib/x86_64-linux-gnu/> --cuda_home <path to folder for CUDA e.g. /usr/local/cuda> --use_tensorrt --tensorrt_home <path to TensorRT home>

# to build with specific version of open-sourced onnx-tensorrt parser configured in cmake/deps.txt
./build.sh  --cudnn_home <path to cuDNN e.g. /usr/lib/x86_64-linux-gnu/> --cuda_home <path to folder for CUDA e.g. /usr/local/cuda> --use_tensorrt --use_tensorrt_oss_parser --tensorrt_home <path to TensorRT home> --skip_submodule_sync

Dockerfile instructions are available here

Note Building with --use_tensorrt_oss_parser with TensorRT 8.X requires additional flag –cmake_extra_defines onnxruntime_USE_FULL_PROTOBUF=ON

NVIDIA Jetson TX1/TX2/Nano/Xavier/Orin

Build Instructions

These instructions are for the latest JetPack SDK 6 for Jetson Orin.

Clone the ONNX Runtime repo on the Jetson host

git clone --recursive https://github.com/microsoft/onnxruntime

Specify the CUDA compiler, or add its location to the PATH.
1. Starting with CUDA 11.8, Jetson users on JetPack 5.0+ can upgrade to the latest CUDA release without updating the JetPack version or Jetson Linux BSP (Board Support Package).
  1. For JetPack 5.x users, CUDA 11.8 and GCC 11 are required to be updated, in order to build latest ONNX Runtime locally.
  2. Check this official blog for CUDA upgrade instruction.
  3. CUDA 12.x is only available to Jetson Orin and newer series (CUDA compute capability >= 8.7). Check here for compute capability datasheet. JetPack 6.0 comes preinstalled with CUDA 12.2
2. CMake can’t automatically find the correct nvcc if it’s not in the PATH. nvcc can be added to PATH via:
```
export PATH="/usr/local/cuda/bin:${PATH}"
```
  or:
```
export CUDACXX="/usr/local/cuda/bin/nvcc"
```
3. Update TensorRT libraries
  1. Jetpack 5.x supports up to TensorRT 8.5. Jetpack 6.0 is equipped with TensorRT 8.6 and can support TensorRT 10.
  2. Jetpack 6.0 users can download latest TensorRT 10 TAR package for jetpack on TensorRT SDK website.
  3. Check here for TensorRT/CUDA support matrix among all ONNX Runtime versions.

Install the ONNX Runtime build dependencies on the Jetpack host:

sudo apt install -y --no-install-recommends \
  build-essential software-properties-common libopenblas-dev \
  libpython3.8-dev python3-pip python3-dev python3-setuptools python3-wheel

Cmake is needed to build ONNX Runtime. The minimum required CMake version is 3.26 (version 3.27.4 has been tested). This can be either installed by:
1. (Unix/Linux) Build from source. Download sources from https://cmake.org/download/ and follow https://cmake.org/install/ to build from source.
2. (Ubuntu) Install deb package via apt repository: e.g https://apt.kitware.com/

Build the ONNX Runtime Python wheel:

Build onnxruntime-gpu wheel with CUDA and TensorRT support (update paths to CUDA/CUDNN/TensorRT libraries if necessary):

./build.sh --config Release --update --build --parallel --build_wheel \
--use_tensorrt --cuda_home /usr/local/cuda --cudnn_home /usr/lib/aarch64-linux-gnu \
--tensorrt_home /usr/lib/aarch64-linux-gnu

Notes:

By default, onnxruntime-gpu wheel file will be captured under path_to/onnxruntime/build/Linux/Release/dist/ (build path can be customized by adding --build_dir followed by a customized path to the build command above).
For a portion of Jetson devices like the Xavier series, higher power mode involves more cores (up to 6) to compute but it consumes more resource when building ONNX Runtime. Set --parallel 2 or smaller in the build command if system is hanging and OOM happens.

oneDNN

See more information on oneDNN (formerly DNNL) here.

Build Instructions

The DNNL execution provider can be built for Intel CPU or GPU. To build for Intel GPU, install Intel SDK for OpenCL Applications or build OpenCL from Khronos OpenCL SDK. Pass in the OpenCL SDK path as dnnl_opencl_root to the build command. Install the latest GPU driver - Windows graphics driver, Linux graphics compute runtime and OpenCL driver.

For CPU

Windows

.\build.bat --use_dnnl

Linux

./build.sh --use_dnnl

For GPU

Windows

.\build.bat --use_dnnl --dnnl_gpu_runtime ocl --dnnl_opencl_root "c:\program files (x86)\intelswtools\sw_dev_tools\opencl\sdk"

Linux

./build.sh --use_dnnl --dnnl_gpu_runtime ocl --dnnl_opencl_root "/opt/intel/sw_dev_tools/opencl-sdk"

Build Phython Wheel

OneDNN EP build supports building Python wheel for both Windows and linux using flag –build_wheel

.\build.bat --config RelWithDebInfo --parallel --build_shared_lib --cmake_generator "Visual Studio 16 2019" --build_wheel --use_dnnl --dnnl_gpu_runtime ocl --dnnl_opencl_root "C:\Program Files (x86)\IntelSWTools\system_studio_2020\OpenCL\sdk"

OpenVINO

See more information on the OpenVINO™ Execution Provider here.

Prerequisites

Install the OpenVINO™ offline/online installer from Intel^® Distribution of OpenVINO™^TM Toolkit Release 2024.3 for the appropriate OS and target hardware:
- Windows - CPU, GPU, NPU.
- Linux - CPU, GPU
Follow documentation for detailed instructions.

2024.3 is the current recommended OpenVINO™ version. OpenVINO™ 2023.3 is minimal OpenVINO™ version requirement.

Configure the target hardware with specific follow on instructions:
- To configure Intel^® Processor Graphics(GPU) please follow these instructions: Windows, Linux
Initialize the OpenVINO™ environment by running the setupvars script as shown below. This is a required step:
- For Windows:
```
 C:\<openvino_install_directory>\setupvars.bat
```
- For Linux:
```
 $ source <openvino_install_directory>/setupvars.sh
```
  Note: If you are using a dockerfile to use OpenVINO™ Execution Provider, sourcing OpenVINO™ won’t be possible within the dockerfile. You would have to explicitly set the LD_LIBRARY_PATH to point to OpenVINO™ libraries location. Refer our dockerfile.

Build Instructions

Windows

.\build.bat --config RelWithDebInfo --use_openvino <hardware_option> --build_shared_lib --build_wheel

Note: The default Windows CMake Generator is Visual Studio 2019, but you can also use the newer Visual Studio 2022 by passing --cmake_generator "Visual Studio 17 2022" to .\build.bat

Linux

./build.sh --config RelWithDebInfo --use_openvino <hardware_option> --build_shared_lib --build_wheel

--build_wheel Creates python wheel file in dist/ folder. Enable it when building from source.
--use_openvino builds the OpenVINO™ Execution Provider in ONNX Runtime.
<hardware_option>: Specifies the default hardware target for building OpenVINO™ Execution Provider. This can be overriden dynamically at runtime with another option (refer to OpenVINO™-ExecutionProvider for more details on dynamic device selection). Below are the options for different Intel target devices.

Refer to Intel GPU device naming convention for specifying the correct hardware target in cases where both integrated and discrete GPU’s co-exist.

Hardware Option	Target Device
`CPU`	Intel^® CPUs
`GPU`	Intel^® Integrated Graphics
`GPU.0`	Intel^® Integrated Graphics
`GPU.1`	Intel^® Discrete Graphics
`NPU`	Intel^® Neural Processor Unit
`HETERO:DEVICE_TYPE_1,DEVICE_TYPE_2,DEVICE_TYPE_3...`	All Intel^® silicons mentioned above
`MULTI:DEVICE_TYPE_1,DEVICE_TYPE_2,DEVICE_TYPE_3...`	All Intel^® silicons mentioned above
`AUTO:DEVICE_TYPE_1,DEVICE_TYPE_2,DEVICE_TYPE_3...`	All Intel^® silicons mentioned above

Specifying Hardware Target for HETERO or Multi or AUTO device Build:

HETERO:DEVICE_TYPE_1,DEVICE_TYPE_2,DEVICE_TYPE_3… The DEVICE_TYPE can be any of these devices from this list [‘CPU’,’GPU’, ‘NPU’]

A minimum of two device’s should be specified for a valid HETERO or MULTI or AUTO device build.

Example's: HETERO:GPU,CPU or AUTO:GPU,CPU or MULTI:GPU,CPU

Disable subgraph partition Feature

Builds the OpenVINO™ Execution Provider in ONNX Runtime with sub graph partitioning disabled.
With this option enabled. Fully supported models run on OpenVINO Execution Provider else they completely fall back to default CPU EP.
To enable this feature during build time. Use --use_openvino <hardware_option>_NO_PARTITION

Usage: --use_openvino CPU_FP32_NO_PARTITION or --use_openvino GPU_FP32_NO_PARTITION or
       --use_openvino GPU_FP16_NO_PARTITION 

For more information on OpenVINO™ Execution Provider's ONNX Layer support, Topology support, and Intel hardware enabled, please refer to the document OpenVINO™-ExecutionProvider

QNN

See more information on the QNN execution provider here.

Prerequisites

Qualcomm AI Engine Direct SDK (Qualcomm Neural Network SDK) Linux/Android/Windows

Build Instructions

Windows (arm64 native build)

build.bat --arm64 --use_qnn --qnn_home=[QNN_SDK path] --build_shared_lib --cmake_generator "Visual Studio 17 2022" --skip_submodule_sync --config Release --build_dir \build\Windows

build python bindings

build.bat --arm64 --use_qnn --qnn_home=[QNN_SDK path] --build_wheel --cmake_generator "Visual Studio 17 2022" --skip_submodule_sync --config Release --build_dir \build\Windows

Linux (x64)

build.py --use_qnn --qnn_home=[QNN_SDK path] --build_shared_lib --skip_submodule_sync --config Release

Android (Cross-Compile):

Please reference Build OnnxRuntime For Android

# on Windows
build.bat --build_shared_lib --skip_submodule_sync --android --config Release --use_qnn --qnn_home [QNN_SDK path] --android_sdk_path [android_SDK path] --android_ndk_path [android_NDK path] --android_abi arm64-v8a --android_api [api-version] --cmake_generator Ninja --build_dir build\Android

# on Linux
build.sh --build_shared_lib --skip_submodule_sync --android --config Release --use_qnn --qnn_home [QNN_SDK path] --android_sdk_path [android_SDK path] --android_ndk_path [android_NDK path] --android_abi arm64-v8a --android_api [api-version] --cmake_generator Ninja --build_dir build/Android

DirectML

See more information on the DirectML execution provider here.

Windows

.\build.bat --use_dml

Notes

The DirectML execution provider supports building for both x64 and x86 architectures. DirectML is only supported on Windows.

Arm Compute Library

See more information on the ACL Execution Provider here.

Build Instructions

You must first build Arm Compute Library 24.07 for your platform as described in the documentation. See here for information on building for Arm®-based devices.

Add the following options to build.sh to enable the ACL Execution Provider:

--use_acl --acl_home=/path/to/ComputeLibrary --acl_libs=/path/to/ComputeLibrary/build

Arm NN

See more information on the Arm NN Execution Provider here.

Prerequisites

Supported backend: i.MX8QM Armv8 CPUs
Supported BSP: i.MX8QM BSP
- Install i.MX8QM BSP: source fsl-imx-xwayland-glibc-x86_64-fsl-image-qt5-aarch64-toolchain-4*.sh
Set up the build environment

source /opt/fsl-imx-xwayland/4.*/environment-setup-aarch64-poky-linux
alias cmake="/usr/bin/cmake -DCMAKE_TOOLCHAIN_FILE=$OECORE_NATIVE_SYSROOT/usr/share/cmake/OEToolchainConfig.cmake"

See here for information on building for Arm-based devices

Build Instructions

./build.sh --use_armnn

The Relu operator is set by default to use the CPU execution provider for better performance. To use the Arm NN implementation build with –armnn_relu flag

./build.sh --use_armnn --armnn_relu

The Batch Normalization operator is set by default to use the CPU execution provider. To use the Arm NN implementation build with –armnn_bn flag

./build.sh --use_armnn --armnn_bn

To use a library outside the normal environment you can set a custom path by providing the –armnn_home and –armnn_libs parameters to define the path to the Arm NN home directory and build directory respectively. The Arm Compute Library home directory and build directory must also be available, and can be specified if needed using –acl_home and –acl_libs respectively.

./build.sh --use_armnn --armnn_home /path/to/armnn --armnn_libs /path/to/armnn/build  --acl_home /path/to/ComputeLibrary --acl_libs /path/to/acl/build

RKNPU

See more information on the RKNPU Execution Provider here.

Prerequisites

Supported platform: RK1808 Linux
See here for information on building for Arm-based devices
Use gcc-linaro-6.3.1-2017.05-x86_64_aarch64-linux-gnu instead of gcc-linaro-6.3.1-2017.05-x86_64_arm-linux-gnueabihf, and modify CMAKE_CXX_COMPILER & CMAKE_C_COMPILER in tool.cmake:

set(CMAKE_CXX_COMPILER aarch64-linux-gnu-g++)
set(CMAKE_C_COMPILER aarch64-linux-gnu-gcc)

Build Instructions

Linux

Download rknpu_ddk to any directory.

Build ONNX Runtime library and test:

 ./build.sh --arm --use_rknpu --parallel --build_shared_lib --build_dir build_arm --config MinSizeRel --cmake_extra_defines RKNPU_DDK_PATH=<Path To rknpu_ddk> CMAKE_TOOLCHAIN_FILE=<Path To tool.cmake> ONNX_CUSTOM_PROTOC_EXECUTABLE=<Path To protoc>

Deploy ONNX runtime and librknpu_ddk.so on the RK1808 board:

 libonnxruntime.so.1.2.0
 onnxruntime_test_all
 rknpu_ddk/lib64/librknpu_ddk.so

AMD Vitis AI

See more information on the Vitis AI Execution Provider here.

Windows

From the Visual Studio Developer Command Prompt or Developer PowerShell, execute the following command:

.\build.bat --use_vitisai --build_shared_lib --parallel --config Release

If you wish to leverage the Python APIs, please include the --build_wheel flag:

.\build.bat --use_vitisai --build_shared_lib --parallel --config Release --build_wheel

You can override also override the installation location by specifying CMAKE_INSTALL_PREFIX via the cmake_extra_defines parameter. e.g.

.\build.bat --use_vitisai --build_shared_lib --parallel --config Release --cmake_extra_defines CMAKE_INSTALL_PREFIX=D:\onnxruntime

Linux

Currently Linux support is only enabled for AMD Adapable SoCs. Please refer to the guidance here for SoC targets.

AMD MIGraphX

See more information on the MIGraphX Execution Provider here.

Prerequisites

Install ROCm
- The MIGraphX execution provider for ONNX Runtime is built and tested with ROCm6.0.0
Install MIGraphX
- The path to MIGraphX installation must be provided via the --migraphx_home parameter.

Build Instructions

Linux

./build.sh --config <Release|Debug|RelWithDebInfo> --parallel --use_migraphx --migraphx_home <path to MIGraphX home>

Dockerfile instructions are available here.

Build Phython Wheel

./build.sh --config Release --build --build_wheel --parallel --use_migraphx --migraphx_home /opt/rocm

Then the python wheels(*.whl) could be found at ./build/Linux/Release/dist.

AMD ROCm

See more information on the ROCm Execution Provider here.

Prerequisites

Install ROCm
- The ROCm execution provider for ONNX Runtime is built and tested with ROCm6.0.0

Build Instructions

Linux

./build.sh --config <Release|Debug|RelWithDebInfo> --parallel --use_rocm --rocm_home <path to ROCm home>

Dockerfile instructions are available here.

Build Phython Wheel

./build.sh --config Release --build --build_wheel --parallel --use_rocm --rocm_home /opt/rocm

Then the python wheels(*.whl) could be found at ./build/Linux/Release/dist.

NNAPI

Usage of NNAPI on Android platforms is via the NNAPI Execution Provider (EP).

See the NNAPI Execution Provider documentation for more details.

The pre-built ONNX Runtime Mobile package for Android includes the NNAPI EP.

If performing a custom build of ONNX Runtime, support for the NNAPI EP or CoreML EP must be enabled when building.

Create a minimal build with NNAPI EP support

Please see the instructions for setting up the Android environment required to build. The Android build can be cross-compiled on Windows or Linux.

Once you have all the necessary components setup, follow the instructions to create the custom build, with the following changes:

Replace --minimal_build with --minimal_build extended to enable support for execution providers that dynamically create kernels at runtime, which is required by the NNAPI EP.
Add --use_nnapi to include the NNAPI EP in the build

Example build commands with the NNAPI EP enabled

Windows example:

<ONNX Runtime repository root>.\build.bat --config MinSizeRel --android --android_sdk_path D:\Android --android_ndk_path D:\Android\ndk\21.1.6352462\ --android_abi arm64-v8a --android_api 29 --cmake_generator Ninja --minimal_build extended --use_nnapi --disable_ml_ops --disable_exceptions --build_shared_lib --skip_tests --include_ops_by_config <config file from model conversion>

Linux example:

<ONNX Runtime repository root>./build.sh --config MinSizeRel --android --android_sdk_path /Android --android_ndk_path /Android/ndk/21.1.6352462/ --android_abi arm64-v8a --android_api 29 --minimal_build extended --use_nnapi --disable_ml_ops --disable_exceptions --build_shared_lib --skip_tests --include_ops_by_config <config file from model conversion>`

CoreML

Usage of CoreML on iOS and macOS platforms is via the CoreML EP.

See the CoreML Execution Provider documentation for more details.

The pre-built ONNX Runtime Mobile package for iOS includes the CoreML EP.

Create a minimal build with CoreML EP support

Please see the instructions for setting up the iOS environment required to build. The iOS/macOS build must be performed on a mac machine.

Once you have all the necessary components setup, follow the instructions to create the custom build, with the following changes:

Replace --minimal_build with --minimal_build extended to enable support for execution providers that dynamically create kernels at runtime, which is required by the CoreML EP.
Add --use_coreml to include the CoreML EP in the build

XNNPACK

Usage of XNNPACK on Android/iOS/Windows/Linux platforms is via the XNNPACK EP.

See the XNNPACK Execution Provider documentation for more details.

The pre-built ONNX Runtime package(onnxruntime-android) for Android includes the XNNPACK EP.

The pre-built ONNX Runtime Mobile package for iOS, onnxruntime-c and onnxruntime-objc in CocoaPods, includes the XNNPACK EP. (Package onnxruntime-objc with XNNPACK will be available since 1.14.)

If performing a custom build of ONNX Runtime, support for the XNNPACK EP must be enabled when building.

Build for Android

Create a minimal build with XNNPACK EP support

Please see the instructions for setting up the Android environment required to build. The Android build can be cross-compiled on Windows or Linux.

Once you have all the necessary components setup, follow the instructions to create the custom build, with the following changes:

Replace --minimal_build with --minimal_build extended to enable support for execution providers that dynamically create kernels at runtime, which is required by the XNNPACK EP.
Add --use_xnnpack to include the XNNPACK EP in the build

Example build commands with the XNNPACK EP enabled

Windows example:

<ONNX Runtime repository root>.\build.bat --config MinSizeRel --android --android_sdk_path D:\Android --android_ndk_path D:\Android\ndk\21.1.6352462\ --android_abi arm64-v8a --android_api 29 --cmake_generator Ninja --minimal_build extended --use_xnnpack --disable_ml_ops --disable_exceptions --build_shared_lib --skip_tests --include_ops_by_config <config file from model conversion>

Linux example:

<ONNX Runtime repository root>./build.sh --config MinSizeRel --android --android_sdk_path /Android --android_ndk_path /Android/ndk/21.1.6352462/ --android_abi arm64-v8a --android_api 29 --minimal_build extended --use_xnnpack --disable_ml_ops --disable_exceptions --build_shared_lib --skip_tests --include_ops_by_config <config file from model conversion>`

If you don’t mind MINIMAL build, you can use the following command to build XNNPACK EP for Android: Linux example:

./build.sh --cmake_generator "Ninja" --android  --android_sdk_path /Android --android_ndk_path /Android/ndk/21.1.6352462/ --android_abi arm64-v8a --android_api 29 --use_xnnpack

Build for iOS (available since 1.14)

A Mac machine is required to build package for iOS. Please follow this guide to set up environment firstly.

Create a minimal build with XNNPACK EP support

Once you have all the necessary components setup, follow the instructions to create the custom build, with the following changes:

Replace --minimal_build with --minimal_build extended to enable support for execution providers that dynamically create kernels at runtime, which is required by the XNNPACK EP.
Add --use_xnnpack to include the XNNPACK EP in the build

<ONNX Runtime repository root>./build.sh --config <Release|Debug|RelWithDebInfo|MinSizeRel> --use_xcode \
           --ios --ios_sysroot iphoneos --osx_arch arm64 --apple_deploy_target <minimal iOS version> --use_xnnpack --minimal_build extended --disable_ml_ops --disable_exceptions --build_shared_lib --skip_tests --include_ops_by_config <config file from model conversion>

Build for Windows

<ONNX Runtime repository root>.\build.bat --config <Release|Debug|RelWithDebInfo> --use_xnnpack

Build for Linux

<ONNX Runtime repository root>./build.sh --config <Release|Debug|RelWithDebInfo> --use_xnnpack

CANN

See more information on the CANN Execution Provider here.

Prerequisites

Install the CANN Toolkit for the appropriate OS and target hardware by following documentation for detailed instructions, please.

Initialize the CANN environment by running the script as shown below.

# Default path, change it if needed.
source /usr/local/Ascend/ascend-toolkit/set_env.sh

Build Instructions

Linux

./build.sh --config <Release|Debug|RelWithDebInfo> --build_shared_lib --parallel --use_cann

Notes

The CANN execution provider supports building for both x64 and aarch64 architectures.
CANN excution provider now is only supported on Linux.

Azure

See the Azure Execution Provider documentation for more details.

Prerequisites

For Linux, before building, please:

install openssl dev package into the system, which is openssl-dev for redhat and libssl-dev for ubuntu.
if have multiple openssl dev versions installed in the system, please set environment variable “OPENSSL_ROOT_DIR” to the desired version, for example:

set OPENSSL_ROOT_DIR=/usr/local/ssl3.x/

Build Instructions

Windows

build.bat --config <Release|Debug|RelWithDebInfo> --build_shared_lib --build_wheel --use_azure

Linux

./build.sh --config <Release|Debug|RelWithDebInfo> --build_shared_lib --build_wheel --use_azure

Build ONNX Runtime with Execution Providers

Contents

Execution Provider Shared Libraries

Built files

Loading the shared providers

CUDA

Prerequisites

Build Instructions

Windows

Linux

Build Options

Notes on older versions of ONNX Runtime, CUDA and Visual Studio

TensorRT

Prerequisites

Build Instructions

Windows

Linux

NVIDIA Jetson TX1/TX2/Nano/Xavier/Orin

Build Instructions

oneDNN

Build Instructions

Windows

Linux

Windows

Linux

Build Phython Wheel

OpenVINO

Prerequisites

Build Instructions

Windows

Linux

Disable subgraph partition Feature

QNN

Prerequisites

Build Instructions

Windows (arm64 native build)

Linux (x64)

Android (Cross-Compile):

DirectML

Windows

Notes

Arm Compute Library

Build Instructions

Arm NN

Prerequisites

Build Instructions

RKNPU

Prerequisites

Build Instructions

Linux

AMD Vitis AI

Windows

Linux

AMD MIGraphX

Prerequisites

Build Instructions

Linux

Build Phython Wheel

AMD ROCm

Prerequisites

Build Instructions

Linux

Build Phython Wheel

NNAPI

Create a minimal build with NNAPI EP support

Example build commands with the NNAPI EP enabled

CoreML

Create a minimal build with CoreML EP support

XNNPACK

Build for Android

Create a minimal build with XNNPACK EP support

Example build commands with the XNNPACK EP enabled

Build for iOS (available since 1.14)

Create a minimal build with XNNPACK EP support

Build for Windows

Build for Linux

CANN

Prerequisites

Build Instructions

Linux