executorch_flutter library

ExecuTorch Flutter Plugin - On-device ML inference with ExecuTorch

This package provides Flutter developers with the ability to run ExecuTorch machine learning models on Android, iOS, macOS, Linux, and Windows with high performance and low latency.

Key Features

• High Performance: Native FFI bindings for minimal latency
• Cross Platform: Identical APIs across all supported platforms
• User-Controlled Resources: Explicit model lifecycle with load/dispose
• Easy Integration: Simple API for loading models and running inference
• Backend Query: Check available hardware acceleration backends

Quick Start

import 'package:executorch_flutter/executorch_flutter.dart';

// Load a model from asset bundle
final model = await loadModelFromAsset('assets/models/model.pte');

// Prepare input data
final inputTensor = TensorData(
  shape: [1, 3, 224, 224],
  dataType: TensorType.float32,
  data: imageBytes,
  name: 'input',
);

// Run inference
final outputs = await model.forward([inputTensor]);

// Process outputs (List<TensorData>)
for (var output in outputs) {
  print('Output shape: ${output.shape}');
}

// Clean up
await model.dispose();

Main Classes

• ExecuTorchModel: Main API for loading and running inference
• TensorData: Tensor data representation
• Backend: Hardware acceleration backend enumeration
• ExecuTorchVersion: Library version information

Processors

• ExecuTorchPreprocessor: Base class for input preprocessing
• ExecuTorchPostprocessor: Base class for output postprocessing
• ExecuTorchProcessor: Combined preprocessing and postprocessing

Platform Support

• Android: API 23+ (Android 6.0+), arm64-v8a architecture
• iOS: iOS 13.0+, arm64 (device only)
• macOS: macOS 11.0+, arm64 (Apple Silicon)
• Linux: x64 architecture
• Windows: x64 architecture

For detailed documentation and examples, see the class documentation.