saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-09 17:28:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/js/web
History
Tianlei Wu d79e3c5791
Extend Attention Bias Broadcast Support (#21710) 
### Description
Previously, MultiHeadAttention supports relative position bias of shape
[1, N, S, T] or [B, N, S, T], and DecoderMaskedMultiHeadAttention
supports [1, N, S, T]. This will extend the support to allow [1, N, S,
T], [B, N, S, T], [B, 1, S, T] and [1, 1, S, T] for CUDA and CPU EPs.

- [x] Rename the input of "relative position bias" to "attention bias"
because it can also be used for other types of bias, like ALiBi
(Attention with Linear Biases) or attention mask.
- [x] Update unfused kernel to support broadcasting 2nd dimension of
attention bias.
- [x] Update efficient attention to support broadcasting 2nd dimension
of attention bias.
- [x] Update operators (MultiHeadAttention,
DecoderMaskedMultiHeadAttention, Attention, PackedAttention,
PackedMultiHeadAttention) to support broadcast attention bias on CUDA
and CPU EPs.
- [x] Update ROCm, DML and WebGPU naming to be consistent. (Note that
those EPs do not support broadcasting attention_bias for now).
- [x] Add attention bias tests for MultiHeadAttention.
- [x] Update operator documents
- [x] Update benchmark script

Other changes:
* Fix some checks in multihead-attention.ts
* Add helper functions to dump tensors given dimensions.
2024-08-16 15:40:04 -07:00
..
docs add Gelu opset-20 to webgpu (#21725) 2024-08-14 09:45:05 -07:00
lib Extend Attention Bias Broadcast Support (#21710) 2024-08-16 15:40:04 -07:00
script [js/webgpu] Support Chrome Canary in unit tests (#21750) 2024-08-15 19:27:54 -07:00
test Extend Attention Bias Broadcast Support (#21710) 2024-08-16 15:40:04 -07:00
.gitignore [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
.npmignore [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
karma.conf.js [js] change default formatter for JavaScript/TypeScript from clang-format to Prettier (#21728) 2024-08-14 16:51:22 -07:00
package-lock.json [js/web] allow op test to use f16 type for inputs/outputs (#21664) 2024-08-08 09:56:37 -07:00
package.json [js/web] allow op test to use f16 type for inputs/outputs (#21664) 2024-08-08 09:56:37 -07:00
README.md [WebNN EP] Add WebNN operators doc to README.md (#20734) 2024-05-20 14:57:40 -07:00
tsconfig.json [js/web] fix ESLint by excluding generated .js from tsconfig.json (#18634) 2023-11-30 09:50:47 -08:00
types.d.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00

README.md

ONNX Runtime Web

ONNX Runtime Web is a Javascript library for running ONNX models on browsers and on Node.js.

ONNX Runtime Web has adopted WebAssembly and WebGL technologies for providing an optimized ONNX model inference runtime for both CPUs and GPUs.

Why ONNX models

The Open Neural Network Exchange (ONNX) is an open standard for representing machine learning models. The biggest advantage of ONNX is that it allows interoperability across different open source AI frameworks, which itself offers more flexibility for AI frameworks adoption.

Why ONNX Runtime Web

With ONNX Runtime Web, web developers can score models directly on browsers with various benefits including reducing server-client communication and protecting user privacy, as well as offering install-free and cross-platform in-browser ML experience.

ONNX Runtime Web can run on both CPU and GPU. On CPU side, WebAssembly is adopted to execute the model at near-native speed. ONNX Runtime Web compiles the native ONNX Runtime CPU engine into WebAssembly backend by using Emscripten, so it supports most functionalities native ONNX Runtime offers, including full ONNX operator coverage, multi-threading, ONNX Runtime Quantization as well as ONNX Runtime Mobile. For performance acceleration with GPUs, ONNX Runtime Web leverages WebGL, a popular standard for accessing GPU capabilities. We are keeping improving op coverage and optimizing performance in WebGL backend.

See Compatibility and Operators Supported for a list of platforms and operators ONNX Runtime Web currently supports.

Usage

Documents

Development

Refer to the following links for development information:

Compatibility

EPs/Browsers Chrome/Edge (Windows) Chrome/Edge (Android) Chrome/Edge (MacOS) Chrome/Edge (iOS) Safari (MacOS) Safari (iOS) Firefox (Windows) Node.js
WebAssembly (CPU) ✔️ ✔️ ✔️ ✔️ ✔️ ✔️ ✔️ ✔️[1]
WebGPU ✔️[2] ✔️[3] ✔️ ❌ ❌ ❌ ❌ ❌
WebGL ✔️[4] ✔️[4] ✔️[4] ✔️[4] ✔️[4] ✔️[4] ✔️[4] ❌
WebNN ✔️[5] ❌ ❌ ❌ ❌ ❌ ❌ ❌
  • [1]: Node.js only support single-threaded wasm EP.
  • [2]: WebGPU requires Chromium v113 or later on Windows. Float16 support requires Chrome v121 or later, and Edge v122 or later.
  • [3]: WebGPU requires Chromium v121 or later on Windows.
  • [4]: WebGL support is in maintenance mode. It is recommended to use WebGPU for better performance.
  • [5]: Requires to launch browser with commandline flag --enable-features=WebMachineLearningNeuralNetwork.

Operators

WebAssembly backend

ONNX Runtime Web currently support all operators in ai.onnx and ai.onnx.ml.

WebGL backend

ONNX Runtime Web currently supports a subset of operators in ai.onnx operator set. See webgl-operators.md for a complete, detailed list of which ONNX operators are supported by WebGL backend.

WebGPU backend

WebGPU backend is still an experimental feature. See webgpu-operators.md for a detailed list of which ONNX operators are supported by WebGPU backend.

WebNN backend

WebNN backend is still an experimental feature. See webnn-operators.md for a detailed list of which ONNX operators are supported by WebNN backend.

License

License information can be found here.