8680244ebc
### Description This change fixes the DLL delay load problem for the WebGPU EP and DirectML EP. See detailed explanation below. ### Problem When onnxruntime.dll uses delay loading for its dependencies, the dependencies are loaded using `LoadLibraryEx()`, which search the directory of process (.exe) instead of this library (onnxruntime.dll). This is a problem for usages of Node.js binding and python binding, because Windows will try to find the dependencies in the directory of node.exe or python.exe, which is not the directory of onnxruntime.dll. There was previous attempt to fix this by loading DirectML.dll in the initialization of onnxruntime nodejs binding, which works for DML EP but is not a good solution because it does not really "delay" the load. For WebGPU, the situation became worse because webgpu_dawn.dll depends on dxil.dll and dxcompiler.dll, which are explicitly dynamically loaded in the code using `LoadLibraryA()`. This has the same problem of the DLL search. ### Solutions For onnxruntime.dll loading its direct dependencies, it can be resolved by set the [`__pfnDliNotifyHook2` hook](https://learn.microsoft.com/en-us/cpp/build/reference/understanding-the-helper-function?view=msvc-170#structure-and-constant-definitions) to load from an absolute path that constructed from the onnxruntime.dll folder and the DLL name. For webgpu_dawn.dll loading dxil.dll and dxcompiler.dll, since they are explicitly loaded in the code, the hook does not work. Instead, it can be resolved by ~~using WIN32 API `SetDllDirectory()` to add the onnxruntime.dll folder to the search path.~~ preloading the 2 DLLs from the onnxruntime.dll folder . |
||
|---|---|---|
| .. | ||
| lib | ||
| script | ||
| src | ||
| test | ||
| .gitignore | ||
| .npmignore | ||
| CMakeLists.txt | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
ONNX Runtime Node.js Binding
ONNX Runtime Node.js binding enables Node.js applications to run ONNX model inference.
Usage
Install the latest stable version:
npm install onnxruntime-node
Refer to ONNX Runtime JavaScript examples for samples and tutorials.
Requirements
ONNXRuntime works on Node.js v16.x+ (recommend v20.x+) or Electron v15.x+ (recommend v28.x+).
The following table lists the supported versions of ONNX Runtime Node.js binding provided with pre-built binaries.
| EPs/Platforms | Windows x64 | Windows arm64 | Linux x64 | Linux arm64 | MacOS x64 | MacOS arm64 |
|---|---|---|---|---|---|---|
| CPU | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
| DirectML | ✔️ | ✔️ | ❌ | ❌ | ❌ | ❌ |
| CUDA | ❌ | ❌ | ✔️[1] | ❌ | ❌ | ❌ |
- [1]: CUDA v11.8.
To use on platforms without pre-built binaries, you can build Node.js binding from source and consume it by npm install <onnxruntime_repo_root>/js/node/. See also instructions for building ONNX Runtime Node.js binding locally.
GPU Support
Right now, the Windows version supports only the DML provider. Linux x64 can use CUDA and TensorRT.
CUDA EP Installation
To use CUDA EP, you need to install the CUDA EP binaries. By default, the CUDA EP binaries are installed automatically when you install the package. If you want to skip the installation, you can pass the --onnxruntime-node-install-cuda=skip flag to the installation command.
npm install onnxruntime-node --onnxruntime-node-install-cuda=skip
You can also use this flag to specify the version of the CUDA: (v11 or v12)
npm install onnxruntime-node --onnxruntime-node-install-cuda=v12
License
License information can be found here.