onnxruntime/js/node
Steven Roussey d5628f52df
link to docs incorrect for js/web/node (#18960)
### Description
link to docs incorrect for js/web/node



### Motivation and Context
Trying to build myself and not yet succeeding.
2024-01-03 17:30:24 -08:00
..
lib [js/node] support manually dispose session (#18655) 2023-12-19 16:20:00 -08:00
script [js] update prepack script to use exact version (#17484) 2023-09-13 00:07:16 -07:00
src [js/node] support manually dispose session (#18655) 2023-12-19 16:20:00 -08:00
test [js] update a few packages (#18499) 2023-11-17 22:40:51 -08:00
.gitignore [node.js binding] aggregate binaries for multiple platforms in single NPM package (#9501) 2021-10-25 20:16:10 -07:00
.npmignore [node.js binding] aggregate binaries for multiple platforms in single NPM package (#9501) 2021-10-25 20:16:10 -07:00
CMakeLists.txt Added DML and CUDA provider support in onnxruntime-node (#16050) 2023-08-25 16:57:06 -07:00
package-lock.json [js] update a few packages (#18499) 2023-11-17 22:40:51 -08:00
package.json [js] update a few packages (#18499) 2023-11-17 22:40:51 -08:00
README.md link to docs incorrect for js/web/node (#18960) 2024-01-03 17:30:24 -08:00
tsconfig.json [js/web] fix typescript type check (#18343) 2023-11-10 16:03:38 -08:00

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 v12.x+ or Electron v5.x+.

Following platforms are supported with pre-built binaries:

  • Windows x64 CPU NAPI_v3
  • Linux x64 CPU NAPI_v3
  • MacOS x64 CPU NAPI_v3

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.

License

License information can be found here.