llama.cpp 在 iOS 上的應用：Swift 整合指南

# 建構框架
mkdir build-ios && cd build-ios
cmake .. -G Xcode \
    -DCMAKE_SYSTEM_NAME=iOS \
    -DCMAKE_OSX_DEPLOYMENT_TARGET=15.0 \
    -DLLAMA_METAL=ON \
    -DBUILD_SHARED_LIBS=OFF
cmake --build . --config Release

import llama

class LlamaEngine {
    private var model: OpaquePointer?
    private var context: OpaquePointer?

    func loadModel(at path: String) throws {
        // 模型參數
        var modelParams = llama_model_default_params()
        modelParams.n_gpu_layers = 99 // 將所有層卸載到 Metal

        // 載入 GGUF 文件
        model = llama_load_model_from_file(path, modelParams)
        guard model != nil else {
            throw LlamaError.modelLoadFailed
        }

        // 建立推論上下文
        var ctxParams = llama_context_default_params()
        ctxParams.n_ctx = 2048      // 上下文視窗大小
        ctxParams.n_threads = 4     // CPU 執行緒（用於非 Metal 運算）
        ctxParams.n_batch = 512     // 提示處理的批次大小

        context = llama_new_context_with_model(model, ctxParams)
        guard context != nil else {
            throw LlamaError.contextCreationFailed
        }
    }

    func unload() {
        if let ctx = context {
            llama_free(ctx)
            context = nil
        }
        if let mdl = model {
            llama_free_model(mdl)
            model = nil
        }
    }

    deinit {
        unload()
    }
}

extension LlamaEngine {
    func generate(
        prompt: String,
        maxTokens: Int = 256,
        temperature: Float = 0.7,
        onToken: @escaping (String) -> Void
    ) -> String {
        guard let ctx = context, let mdl = model else { return "" }

        // 對提示進行分詞
        let promptTokens = tokenize(prompt)

        // 建立用於提示處理的批次
        var batch = llama_batch_init(Int32(promptTokens.count), 0, 1)
        for (i, token) in promptTokens.enumerated() {
            llama_batch_add(&batch, token, Int32(i), [0], i == promptTokens.count - 1)
        }

        // 處理提示
        llama_decode(ctx, batch)
        llama_batch_free(batch)

        // 生成 token
        var output = ""
        for _ in 0..<maxTokens {
            let logits = llama_get_logits(ctx)

            // 取樣下一個 token
            let token = sampleToken(logits: logits!, temperature: temperature)

            // 檢查是否為序列結尾
            if llama_token_is_eog(mdl, token) { break }

            // 將 token 解碼為字串
            let piece = decodeToken(token)
            output += piece
            onToken(piece)

            // 準備下一個批次
            var nextBatch = llama_batch_init(1, 0, 1)
            llama_batch_add(&nextBatch, token, Int32(promptTokens.count + output.count), [0], true)
            llama_decode(ctx, nextBatch)
            llama_batch_free(nextBatch)
        }

        return output
    }

    private func tokenize(_ text: String) -> [llama_token] {
        let maxTokens = Int32(text.utf8.count + 16)
        var tokens = [llama_token](repeating: 0, count: Int(maxTokens))
        let count = llama_tokenize(model, text, Int32(text.utf8.count),
                                   &tokens, maxTokens, true, false)
        return Array(tokens.prefix(Int(count)))
    }

    private func decodeToken(_ token: llama_token) -> String {
        var buf = [CChar](repeating: 0, count: 64)
        let len = llama_token_to_piece(model, token, &buf, 64, 0, false)
        return String(cString: Array(buf.prefix(Int(len))) + [0])
    }
}

// 載入前檢查可用記憶體
func canLoadModel(sizeBytes: Int) -> Bool {
    let available = os_proc_available_memory()
    // 為應用程式和作業系統保留 500MB 餘量
    return available > sizeBytes + 500_000_000
}

// 處理記憶體警告
func didReceiveMemoryWarning() {
    engine.unload()
    // 顯示「模型已卸載」訊息，提供重新載入選項
}

let modelPath = Bundle.main.path(forResource: "model", ofType: "gguf")!

let documentsURL = FileManager.default
    .urls(for: .documentDirectory, in: .userDomainMask)[0]
let modelURL = documentsURL.appendingPathComponent("model.gguf")