kangkang/康康/AI/MNN/MNNLLMBridge.mm

//
//  MNNLLMBridge.mm
//  康康
//
//  ObjC++ 实现。device 真机用 <MNN/llm/llm.hpp>;模拟器编为桩(返回不可用,上层回退 MLX)。
//

#import "MNNLLMBridge.h"
#include <sys/sysctl.h>

// MARK: - 性能统计(私有 readwrite 重声明)
@interface MNNGenerateStats ()
@property (nonatomic, readwrite) int promptTokens;
@property (nonatomic, readwrite) int genTokens;
@property (nonatomic, readwrite) double prefillMs;
@property (nonatomic, readwrite) double decodeMs;
@end

@implementation MNNGenerateStats
- (double)decodeTokensPerSecond {
    return self.decodeMs > 0 ? (self.genTokens / (self.decodeMs / 1000.0)) : 0;
}
@end

// MARK: - SME2 / 可用性探测(device + simulator 都可编)

static BOOL kk_sysctlFlag(const char *name) {
    int64_t v = 0; size_t sz = sizeof(v);
    if (sysctlbyname(name, &v, &sz, NULL, 0) != 0) return NO;
    return v != 0;
}

#if TARGET_OS_SIMULATOR

// ============ 模拟器桩:无真实 MNN ============
@implementation MNNLLMBridge
+ (BOOL)isAvailable { return NO; }
+ (BOOL)cpuSupportsSME2 { return NO; }
- (nullable instancetype)initWithConfigPath:(NSString *)configPath { return nil; }
- (BOOL)isLoaded { return NO; }
- (MNNGenerateStats *)generateText:(NSString *)prompt maxTokens:(int)maxTokens
                           onToken:(void (^)(NSString *))onToken { return [MNNGenerateStats new]; }
- (nullable MNNGenerateStats *)analyzeImages:(NSArray<NSString *> *)imagePaths prompt:(NSString *)prompt
                                   maxTokens:(int)maxTokens onToken:(void (^)(NSString *))onToken
                                       error:(NSError **)error {
    if (error) *error = [NSError errorWithDomain:@"MNN" code:-1
                          userInfo:@{NSLocalizedDescriptionKey: @"MNN 在模拟器不可用"}];
    return nil;
}
- (void)cancel {}
@end

#else

// ============ 真机:真实 MNN-LLM ============
// MNN 第三方头文件的文档注释不规范,会触发一堆 -Wdocumentation 警告(Executor/
// Tensor/Interpreter/ImageProcess.hpp)。只在解析 MNN 头时关掉该警告,不影响本项目。
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wdocumentation"
#include <MNN/llm/llm.hpp>
#pragma clang diagnostic pop
#include <string>
#include <ostream>
#include <streambuf>
#include <atomic>

using MNN::Transformer::Llm;

namespace {
/// 把 MNN 写入 ostream 的解码文本转成 NSString 回调;按 UTF-8 完整边界聚合,避免截断多字节。
class TokenStreamBuf : public std::streambuf {
public:
    TokenStreamBuf(void (^onToken)(NSString *), std::atomic<bool> *cancel)
        : _onToken(onToken), _cancel(cancel) {}
    void flush() {
        if (_pending.empty()) return;
        emitPending(); // 末尾尽力 emit(即便非完整 UTF-8 也交出去)
        _pending.clear();
    }
protected:
    std::streamsize xsputn(const char *s, std::streamsize n) override {
        append(s, (size_t)n);
        return n;
    }
    int overflow(int c) override {
        if (c != EOF) { char ch = (char)c; append(&ch, 1); }
        return c;
    }
private:
    void append(const char *s, size_t n) {
        if (_cancel && _cancel->load()) return; // 已取消,吞掉不回调
        _pending.append(s, n);
        // 仅当整个 pending 是合法 UTF-8 才 emit(token 通常是完整字/词,边界自然对齐)
        NSString *str = [[NSString alloc] initWithBytes:_pending.data()
                                                 length:_pending.size()
                                               encoding:NSUTF8StringEncoding];
        if (str) { if (_onToken) _onToken(str); _pending.clear(); }
    }
    void emitPending() {
        NSString *str = [[NSString alloc] initWithBytes:_pending.data()
                                                 length:_pending.size()
                                               encoding:NSUTF8StringEncoding];
        if (str && _onToken) _onToken(str);
    }
    void (^_onToken)(NSString *);
    std::atomic<bool> *_cancel;
    std::string _pending;
};
} // namespace

@implementation MNNLLMBridge {
    Llm *_llm;
    std::atomic<bool> _cancel;
    BOOL _loaded;
}

+ (BOOL)isAvailable { return YES; }

+ (BOOL)cpuSupportsSME2 {
    // Apple 通过 sysctl 暴露 ARM 特性位:FEAT_SME2(A19/iPhone17+)。
    return kk_sysctlFlag("hw.optional.arm.FEAT_SME2");
}

- (nullable instancetype)initWithConfigPath:(NSString *)configPath {
    self = [super init];
    if (!self) return nil;
    _cancel = false;
    _llm = Llm::createLLM(std::string(configPath.UTF8String));
    if (_llm == nullptr) return nil;
    _loaded = _llm->load();
    if (!_loaded) { Llm::destroy(_llm); _llm = nullptr; return nil; }
    return self;
}

- (void)dealloc {
    if (_llm) { Llm::destroy(_llm); _llm = nullptr; }
}

- (BOOL)isLoaded { return _loaded; }

- (void)cancel { _cancel = true; }

// 统一生成:full 已是最终 prompt(文本,或含 <img>路径</img> 标签)。
// 多模态模型 createLLM 返回 Omni,response 解析 <img> 标签并对路径 CV::imread(OMNI 框架内)。
- (MNNGenerateStats *)runResponse:(NSString *)full
                        maxTokens:(int)maxTokens
                          onToken:(void (^)(NSString *))onToken {
    _cancel = false;
    TokenStreamBuf buf(onToken, &_cancel);
    std::ostream os(&buf);
    if (_llm) {
        _llm->response(std::string(full.UTF8String), &os, nullptr, maxTokens);
    }
    buf.flush();
    return [self statsFromContext];
}

- (MNNGenerateStats *)generateText:(NSString *)prompt
                         maxTokens:(int)maxTokens
                           onToken:(void (^)(NSString *))onToken {
    return [self runResponse:prompt maxTokens:maxTokens onToken:onToken];
}

- (nullable MNNGenerateStats *)analyzeImages:(NSArray<NSString *> *)imagePaths
                                      prompt:(NSString *)prompt
                                   maxTokens:(int)maxTokens
                                     onToken:(void (^)(NSString *))onToken
                                       error:(NSError **)error {
    // 在 prompt 前拼 <img>本地路径</img>;Omni 解析标签并对路径 imread(需 OMNI 框架)。
    NSMutableString *full = [NSMutableString string];
    for (NSString *p in imagePaths) {
        [full appendFormat:@"<img>%@</img>", p];
    }
    [full appendString:prompt];
    return [self runResponse:full maxTokens:maxTokens onToken:onToken];
}

- (MNNGenerateStats *)statsFromContext {
    MNNGenerateStats *s = [MNNGenerateStats new];
    if (_llm) {
        const MNN::Transformer::LlmContext *ctx = _llm->getContext();
        if (ctx) {
            s.promptTokens = ctx->prompt_len;
            s.genTokens = ctx->gen_seq_len;
            s.prefillMs = ctx->prefill_us / 1000.0;
            s.decodeMs = ctx->decode_us / 1000.0;
        }
    }
    return s;
}

@end

#endif