saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-30 23:18:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/js/web/lib/wasm
History
Yulong Wang 35697d2421
[js/webnn] update API of session options for WebNN (#20816) 
### Description

This PR is an API-only change to address the requirements being
discussed in #20729.

There are multiple ways that users may create an ORT session by
specifying the session options differently.

All the code snippet below will use the variable `webnnOptions` as this:
```js
const myWebnnSession = await ort.InferenceSession.create('./model.onnx', {
   executionProviders: [
     webnnOptions
   ]
});
```

### The old way (backward-compatibility)

```js
// all-default, name only
const webnnOptions_0 = 'webnn';

// all-default, properties omitted
const webnnOptions_1 = { name: 'webnn' };

// partial
const webnnOptions_2 = {
  name: 'webnn',
  deviceType: 'cpu'
};

// full
const webnnOptions_3 = {
  name: 'webnn',
  deviceType: 'gpu',
  numThreads: 1,
  powerPreference: 'high-performance'
};
```

### The new way (specify with MLContext)

```js
// options to create MLcontext
const options = {
  deviceType: 'gpu',
  powerPreference: 'high-performance'
};

const myMlContext = await navigator.ml.createContext(options);

// options for session options
const webnnOptions = {
  name: 'webnn',
  context: myMlContext,
  ...options
};
```

This should throw (because no deviceType is specified):
```js
const myMlContext = await navigator.ml.createContext({ ... });
const webnnOptions = {
  name: 'webnn',
  context: myMlContext
};
```

### Interop with WebGPU
```js
// get WebGPU device
const adaptor = await navigator.gpu.requestAdapter({ ... });
const device = await adaptor.requestDevice({ ... });

// set WebGPU adaptor and device
ort.env.webgpu.adaptor = adaptor;
ort.env.webgpu.device = device;

const myMlContext = await navigator.ml.createContext(device);
const webnnOptions = {
  name: 'webnn',
  context: myMlContext,
  gpuDevice: device
};
```

This should throw (because cannot specify both gpu device and MLContext
option at the same time):
```js
const webnnOptions = {
  name: 'webnn',
  context: myMlContext,
  gpuDevice: device,
  deviceType: 'gpu'
};
```
2024-05-31 03:25:14 -07:00
..
jsep [js/webgpu] Fix mha name (#20860) 2024-05-30 00:01:06 -07:00
proxy-worker [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
proxy-messages.ts
proxy-wrapper.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
run-options.ts
session-handler-inference.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
session-handler-training.ts
session-options.ts [js/webnn] update API of session options for WebNN (#20816) 2024-05-31 03:25:14 -07:00
wasm-common.ts
wasm-core-impl.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
wasm-factory.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
wasm-training-core-impl.ts
wasm-types.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
wasm-utils-env.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
wasm-utils-import.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
wasm-utils-load-file.ts [js/web] optimize module export and deployment (#20165) 2024-05-20 09:51:16 -07:00
wasm-utils.ts