feat(AI/MNN): 集成 MNN.xcframework + ObjC++ 桥(LLM+SME2,Phase 1-2)

挑战赛考核点要求 Qwen + MNN + SME2 + CPU 端侧推理,MLX(GPU)不满足。本提交打通原生 MNN 集成的工程层: - scripts/build-mnn-xcframework.sh:从 alibaba/MNN 源码构建 device+sim arm64 双切片 xcframework,MNN_BUILD_LLM=ON 导出 llm/llm.hpp,MNN_SME2=ON (KleidiAI 运行时自动路由:A19/iPhone17 走 SME2,A17 回退 NEON) - MNNLLMBridge.{h,mm}:ObjC++ 封装 MNN Llm 的加载/流式生成,streambuf 按 UTF-8 边界聚合回调,getContext() 取 prefill/decode 算 tok/s;模拟器编为桩 (走 MLX 兜底),SME2 经 sysctl hw.optional.arm.FEAT_SME2 探测 - pbxproj:链接 MNN.xcframework + bridging header - 二进制 gitignore,由脚本本地生成防历史膨胀模拟器 BUILD SUCCEEDED(0 error),xcframework 处理 + 桥编译 + 链接通过。下一步 Phase 3:MNNBackend + AIRuntime 双后端路由。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-08 18:31:02 +08:00
parent 06484d09ff
commit afc6a79dd7
6 changed files with 300 additions and 0 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -2,3 +2,6 @@
 /Models/
 /build/
 .DS_Store
+
+# MNN 预编译二进制:由 scripts/build-mnn-xcframework.sh 本地生成,不入库防历史膨胀
+/Frameworks/MNN.xcframework/
--- a/scripts/build-mnn-xcframework.sh
+++ b/scripts/build-mnn-xcframework.sh
@@ -0,0 +1,50 @@
+#!/bin/sh
+# 构建 MNN.xcframework(device arm64 + simulator arm64),含 LLM 引擎 + SME2。
+# 产物输出到 康康/../Frameworks/MNN.xcframework(被 .gitignore,不入库,防历史膨胀)。
+#
+# 用法:
+#   MNN_SRC=/path/to/MNN  sh scripts/build-mnn-xcframework.sh
+# 需求:CMake 3.14+、Xcode、约 10-40 分钟。
+#
+# 关键 flag:
+#   MNN_BUILD_LLM=ON     —— 编入 llm 引擎(并导出 llm/llm.hpp),自动开 MNN_LOW_MEMORY
+#   MNN_SME2=ON          —— CMake 默认 ON,A19/iPhone17 运行时经 KleidiAI 自动启用,A17 回退 NEON
+#   MNN_METAL=OFF        —— 考核走 CPU+SME2,关 Metal 保持精简
+#   MNN_BUILD_LLM_OMNI   —— 如需 VL(图→文)再开,会额外拉 OpenCV/Audio(本脚本默认不开,文本优先)
+set -e
+
+MNN_SRC="${MNN_SRC:-/Users/xuhuayong/apps/MNN-src}"
+OUT_DIR="$(cd "$(dirname "$0")/.." && pwd)/Frameworks"
+TOOLCHAIN_NEW="${MNN_SRC}/cmake/ios.toolchain.new.cmake"
+EXTRA="-DMNN_BUILD_LLM=ON -DMNN_METAL=OFF -DMNN_ARM82=true -DMNN_SME2=ON"
+COMMON="-DCMAKE_BUILD_TYPE=Release -DENABLE_BITCODE=0 -DMNN_AAPL_FMWK=1 -DMNN_SEP_BUILD=0 -DMNN_BUILD_SHARED_LIBS=false -DMNN_USE_THREAD_POOL=OFF"
+
+export DEVELOPER_DIR="/Applications/Xcode.app/Contents/Developer"
+cd "$MNN_SRC"
+
+# 新版 ios-cmake toolchain(支持 SIMULATORARM64;MNN 自带的旧版只支持 x86_64 模拟器)
+if [ ! -f "$TOOLCHAIN_NEW" ]; then
+  curl -sL "https://raw.githubusercontent.com/leetal/ios-cmake/master/ios.toolchain.cmake" -o "$TOOLCHAIN_NEW"
+fi
+
+# device arm64
+rm -rf build-dev-arm64 && mkdir build-dev-arm64 && cd build-dev-arm64
+cmake .. $COMMON $EXTRA -DCMAKE_TOOLCHAIN_FILE="$TOOLCHAIN_NEW" -DPLATFORM=OS64 -DDEPLOYMENT_TARGET=17.0
+make MNN -j16
+cd ..
+
+# simulator arm64
+rm -rf build-sim-arm64 && mkdir build-sim-arm64 && cd build-sim-arm64
+cmake .. $COMMON $EXTRA -DCMAKE_TOOLCHAIN_FILE="$TOOLCHAIN_NEW" -DPLATFORM=SIMULATORARM64 -DDEPLOYMENT_TARGET=17.0
+make MNN -j16
+cd ..
+
+# 合成 xcframework
+rm -rf "$OUT_DIR/MNN.xcframework"
+mkdir -p "$OUT_DIR"
+xcrun xcodebuild -create-xcframework \
+  -framework build-dev-arm64/MNN.framework \
+  -framework build-sim-arm64/MNN.framework \
+  -output "$OUT_DIR/MNN.xcframework"
+
+echo "✅ 输出: $OUT_DIR/MNN.xcframework"
--- a/康康.xcodeproj/project.pbxproj
+++ b/康康.xcodeproj/project.pbxproj
@@ -10,6 +10,7 @@
 		FEED000000000000DEAD0001 /* MLXLLM in Frameworks */ = {isa = PBXBuildFile; productRef = FEED000000000000DEAD0003 /* MLXLLM */; };
 		FEED000000000000DEAD0002 /* MLXLMCommon in Frameworks */ = {isa = PBXBuildFile; productRef = FEED000000000000DEAD0004 /* MLXLMCommon */; };
 		FEED000000000000DEAD0005 /* MLXVLM in Frameworks */ = {isa = PBXBuildFile; productRef = FEED000000000000DEAD0006 /* MLXVLM */; };
+		FEEDFACE000000000000F002 /* MNN.xcframework in Frameworks */ = {isa = PBXBuildFile; fileRef = FEEDFACE000000000000F001 /* MNN.xcframework */; };
 /* End PBXBuildFile section */

 /* Begin PBXContainerItemProxy section */
@@ -33,6 +34,7 @@
 		5E463CF92FC403BB0089145B /* 康康.app */ = {isa = PBXFileReference; explicitFileType = wrapper.application; includeInIndex = 0; path = "康康.app"; sourceTree = BUILT_PRODUCTS_DIR; };
 		5E463D082FC403BC0089145B /* 康康Tests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = "康康Tests.xctest"; sourceTree = BUILT_PRODUCTS_DIR; };
 		5E463D122FC403BC0089145B /* 康康UITests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = "康康UITests.xctest"; sourceTree = BUILT_PRODUCTS_DIR; };
+		FEEDFACE000000000000F001 /* MNN.xcframework */ = {isa = PBXFileReference; lastKnownFileType = wrapper.xcframework; name = MNN.xcframework; path = Frameworks/MNN.xcframework; sourceTree = "<group>"; };
 /* End PBXFileReference section */

 /* Begin PBXFileSystemSynchronizedRootGroup section */
@@ -61,6 +63,7 @@
 				FEED000000000000DEAD0001 /* MLXLLM in Frameworks */,
 				FEED000000000000DEAD0002 /* MLXLMCommon in Frameworks */,
 				FEED000000000000DEAD0005 /* MLXVLM in Frameworks */,
+				FEEDFACE000000000000F002 /* MNN.xcframework in Frameworks */,
 			);
 			runOnlyForDeploymentPostprocessing = 0;
 		};
@@ -88,6 +91,7 @@
 				5E463D0B2FC403BC0089145B /* 康康Tests */,
 				5E463D152FC403BC0089145B /* 康康UITests */,
 				5E463CFA2FC403BB0089145B /* Products */,
+				FEEDFACE000000000000F001 /* MNN.xcframework */,
 			);
 			sourceTree = "<group>";
 		};
@@ -443,6 +447,8 @@
 				PRODUCT_BUNDLE_IDENTIFIER = com.xuhuayong.kangkang;
 				PRODUCT_NAME = "$(TARGET_NAME)";
 				REGISTER_APP_GROUPS = YES;
+				FRAMEWORK_SEARCH_PATHS = "$(PROJECT_DIR)/Frameworks";
+				SWIFT_OBJC_BRIDGING_HEADER = "康康/康康-Bridging-Header.h";
 				SDKROOT = auto;
 				STRING_CATALOG_GENERATE_SYMBOLS = YES;
 				SUPPORTED_PLATFORMS = "iphoneos iphonesimulator";
@@ -497,6 +503,8 @@
 				PRODUCT_BUNDLE_IDENTIFIER = com.xuhuayong.kangkang;
 				PRODUCT_NAME = "$(TARGET_NAME)";
 				REGISTER_APP_GROUPS = YES;
+				FRAMEWORK_SEARCH_PATHS = "$(PROJECT_DIR)/Frameworks";
+				SWIFT_OBJC_BRIDGING_HEADER = "康康/康康-Bridging-Header.h";
 				SDKROOT = auto;
 				STRING_CATALOG_GENERATE_SYMBOLS = YES;
 				SUPPORTED_PLATFORMS = "iphoneos iphonesimulator";
--- a/康康/AI/MNN/MNNLLMBridge.h
+++ b/康康/AI/MNN/MNNLLMBridge.h
@@ -0,0 +1,55 @@
+//
+//  MNNLLMBridge.h
+//  康康
+//
+//  Objective-C 接口,封装 MNN-LLM(Qwen)的加载与流式推理。
+//  真实实现在 .mm 中以 ObjC++ 调用 <MNN/llm/llm.hpp>;模拟器下编为可用性返回 NO 的桩
+//  (MNN.framework 仅 device arm64 切片有真实 CPU/SME2 内核,模拟器走 MLX 兜底)。
+//
+
+#import <Foundation/Foundation.h>
+
+NS_ASSUME_NONNULL_BEGIN
+
+/// 末次生成的性能统计(取自 MNN LlmContext)。
+@interface MNNGenerateStats : NSObject
+@property (nonatomic, readonly) int promptTokens;
+@property (nonatomic, readonly) int genTokens;
+@property (nonatomic, readonly) double prefillMs;
+@property (nonatomic, readonly) double decodeMs;
+/// 解码速率 tok/s = genTokens / (decodeMs/1000)。demo 卖点 #6 / Live Activity 用。
+@property (nonatomic, readonly) double decodeTokensPerSecond;
+@end
+
+@interface MNNLLMBridge : NSObject
+
+/// 本构建是否含真实 MNN 运行时(device=YES,simulator 桩=NO)。
+ (BOOL)isAvailable;
+/// CPU 是否支持 SME2(运行时探测);A19/iPhone17 YES,A17/iPhone15Pro NO。仅用于 UI 展示加速状态。
+ (BOOL)cpuSupportsSME2;
+
+/// 用 MNN llm 的 config.json 路径加载模型(目录含 llm.mnn / 权重 / tokenizer)。失败返回 nil。
+- (nullable instancetype)initWithConfigPath:(NSString *)configPath;
+
+@property (nonatomic, readonly) BOOL isLoaded;
+
+/// 纯文本流式生成。onToken 每解码出一段文本回调一次(在调用线程,同步阻塞直到生成结束)。
+/// 返回末次统计。
+- (MNNGenerateStats *)generateText:(NSString *)prompt
+                         maxTokens:(int)maxTokens
+                           onToken:(void (^)(NSString *piece))onToken;
+
+/// 图→文(VL,需 MNN_BUILD_LLM_OMNI 构建)。imagePaths 为本地文件路径。
+/// 当前文本构建未含 OMNI 时返回 nil 并置 error。
+- (nullable MNNGenerateStats *)analyzeImages:(NSArray<NSString *> *)imagePaths
+                                      prompt:(NSString *)prompt
+                                   maxTokens:(int)maxTokens
+                                     onToken:(void (^)(NSString *piece))onToken
+                                       error:(NSError *_Nullable *_Nullable)error;
+
+/// 请求取消当前生成(best-effort:置标志,后续 token 不再回调)。
+- (void)cancel;
+
+@end
+
+NS_ASSUME_NONNULL_END
--- a/康康/AI/MNN/MNNLLMBridge.mm
+++ b/康康/AI/MNN/MNNLLMBridge.mm
@@ -0,0 +1,178 @@
+//
+//  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 ============
+#include <MNN/llm/llm.hpp>
+#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; }
+
+- (MNNGenerateStats *)generateText:(NSString *)prompt
+                         maxTokens:(int)maxTokens
+                           onToken:(void (^)(NSString *))onToken {
+    _cancel = false;
+    TokenStreamBuf buf(onToken, &_cancel);
+    std::ostream os(&buf);
+    if (_llm) {
+        _llm->response(std::string(prompt.UTF8String), &os, nullptr, maxTokens);
+    }
+    buf.flush();
+    return [self statsFromContext];
+}
+
+- (nullable MNNGenerateStats *)analyzeImages:(NSArray<NSString *> *)imagePaths
+                                      prompt:(NSString *)prompt
+                                   maxTokens:(int)maxTokens
+                                     onToken:(void (^)(NSString *))onToken
+                                       error:(NSError **)error {
+    // VL 需 MNN_BUILD_LLM_OMNI 构建(OpenCV 解码图像)。当前文本构建不含,显式报错。
+    if (error) *error = [NSError errorWithDomain:@"MNN" code:-2
+                          userInfo:@{NSLocalizedDescriptionKey: @"当前 MNN 构建未含 VL(OMNI),请用 OMNI 框架"}];
+    return nil;
+}
+
+- (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
--- a/康康/康康-Bridging-Header.h
+++ b/康康/康康-Bridging-Header.h
@@ -0,0 +1,6 @@
+//
+//  康康-Bridging-Header.h
+//  把 Objective-C 接口暴露给 Swift。
+//
+
+#import "AI/MNN/MNNLLMBridge.h"