Function: loadModel()

loadModel(modelPath, options?): Model

Defined in: core/model.ts:126

Loads and compiles an ExecuTorch .pte model from the local filesystem.

The model is loaded synchronously into native memory. Prefer calling this inside a worklet runtime thread (via wrapAsync) to avoid blocking the JS thread during compilation.

Parameters

modelPath

string

The absolute local path to the .pte model file.

options?

LoadModelOptions

Optional loading configuration. See LoadModelOptions.

Returns

Model

The compiled Model instance, ready for execution.

Throws

Thrown with code LOAD_FAILED if the model file cannot be opened, has an invalid format, or fails native initialization.

See

wrapAsync

Example

const model = loadModel('/path/to/model.pte');
const input = tensor('float32', [1, 3, 224, 224]);
const output = tensor('float32', [1, 1000]);
try {
  model.execute('forward', [input], [output]);
  // ...
} finally {
  input.dispose();
  output.dispose();
  model.dispose();
}