ExecuTorch

// Initialize ExecuTorch module
let module = try ETModule(path: "model.pte")
// Run inference with tensors
let outputs = try module.forward([inputTensor])
// Process results
let result = outputs[0]

// Load model from assets
val module = Module.load(assetFilePath("model.pte"))
// Execute with tensor input
val outputs = module.forward(inputTensor)
// Extract prediction results
val prediction = outputs[0].dataAsFloatArray

// Initialize ExecuTorch module
ETModule *module = [[ETModule alloc] initWithPath:@"model.pte" error:nil];
// Run inference with tensors
NSArray *outputs = [module forwardWithInputs:@[inputTensor] error:nil];
// Process results
ETTensor *result = outputs[0];

// Load model from ArrayBuffer
const module = et.Module.load(buffer);
// Create input tensor from data
const inputTensor = et.Tensor.fromIter(tensorData, shape);
// Run inference
const output = module.forward(inputTensor);

import ExecuTorch
import AVFoundation

// Initialize multimodal runner with audio support
let runner = try MultimodalRunner(
    modelPath: "model.pte",
    visionPath: "vision.pte",
    audioPath: "audio.pte",
    tokenizerPath: tokenizerPath,
    temperature: 0.7
)

// Process audio and image inputs
let audioTensor = AudioProcessor.preprocess(audioURL)
let imageTensor = ImageProcessor.preprocess(uiImage)

// Generate with audio + vision + text
let result = try runner.generateMultimodal(
    prompt: "Describe what you hear and see",
    audio: audioTensor,
    image: imageTensor,
    maxTokens: 512
)

// Stream tokens to UI
result.tokens.forEach { token in
    DispatchQueue.main.async {
        responseText += token
    }
}

import org.pytorch.executorch.MultimodalRunner
import android.media.MediaRecorder

// Initialize multimodal runner with audio
val runner = MultimodalRunner.create(
    modelPath = "model.pte",
    visionPath = "vision.pte",
    audioPath = "audio.pte",
    tokenizerPath = tokenizerPath,
    temperature = 0.7f
)

// Process audio and image inputs
val audioTensor = AudioProcessor.preprocess(audioFile)
val imageTensor = ImageProcessor.preprocess(bitmap)

// Generate with audio + vision + text
val result = runner.generateMultimodal(
    prompt = "Describe what you hear and see",
    audio = audioTensor,
    image = imageTensor,
    maxTokens = 512
)

// Display streaming response
result.tokens.forEach { token ->
    runOnUiThread {
        responseView.append(token)
    }
}