|
- Build ONNX Runtime | onnxruntime
Build ONNX Runtime from source if you need to access a feature that is not already in a released package For production deployments, it’s strongly recommended to build only from an official release branch
- Build from source | onnxruntime
This step assumes that you are in the root of the onnxruntime-genai repo All of the build commands below have a --config argument, which takes the following options:
- Build for inferencing | onnxruntime
You can either build GCC from source code by yourself, or get a prebuilt one from a vendor like Ubuntu, linaro Choosing the same compiler version as your target operating system is best
- Build with different EPs | onnxruntime
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
- Custom build | onnxruntime
Customize the ONNX Runtime binaries, including building with a reduced set of operators
- Build from Source - onnxruntime
The matrix below lists the versions of individual dependencies of onnxruntime-extensions These are the configurations that are routinely and extensively verified by our CI
- Install ONNX Runtime | onnxruntime
Download the onnxruntime-android AAR hosted at MavenCentral, change the file extension from aar to zip, and unzip it Include the header files from the headers folder, and the relevant libonnxruntime so dynamic library from the jni folder in your NDK project
- Build for web | onnxruntime
If you build a part of the artifacts from source, a common practice is to run npm run pull:wasm to pull a full set of prebuilt artifacts and then copy your build artifacts (follow instructions below) to the target folder, so you don’t need to build for 6 times
|
|
|