tim/kangkang
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

```

Browse Source 
feat(iOS): 更新MNN后端模型配置优化性能

将MNN主模型从Qwen3.5-4B(~2.64GiB)降级为Qwen3.5-2B(~1.1GiB)，因为4B版本
实测运行过慢，影响用户体验。iPhone17+/SME2设备使用2B模型，保留MLX
兜底方案用于模拟器和备用场景，确保AI推理性能和存储效率的平衡。
```
This commit is contained in:
link2026
2026-06-09 22:20:07 +08:00
parent ca5a3fa38b
commit b79ae54b7b
40 changed files with 1327 additions and 452 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CLAUDE.md
View File

@@ -24,7 +24,7 @@
| 图表 | Swift Charts | iOS 16+ 原生 |
| **AI 运行时(主)** | **MNN (alibaba) + Arm SME2 + CPU** | 挑战赛考核点:Qwen + MNN + SME2 端侧 CPU 推理。device-only(xcframework 见 `scripts/build-mnn-xcframework.sh`),A19/iPhone17 启用 SME2、A17 回退 NEON。经 `MNNLLMBridge`(ObjC++)→ `MNNBackend` |
| **AI 运行时(兜底)** | **MLX Swift (Apple 官方,Metal GPU)** | 双后端:`InferenceEngine` 切换,模拟器/兜底用 MLX。不要建议 Core ML / llama.cpp / Ollama |
| LLM | MNN 主:Qwen3.5-4B(`taobao-mnn/Qwen3.5-4B-MNN`,~2.64GiB);MLX 兜底:Qwen3.5-2B-4bit | 文本生成、关键词抽取、趋势解读 |
| LLM | MNN 主(iPhone17+/SME2):Qwen3.5-2B(`taobao-mnn/Qwen3.5-2B-MNN`,~1.1GiB);MLX 兜底:Qwen3.5-2B-4bit | 文本生成、关键词抽取、趋势解读。4B 实测过慢已退回 2B |
| VL | Qwen3-VL-4B-Instruct 4bit (MLX `mlx-community/Qwen3-VL-4B-Instruct-4bit`) | 拍照→结构化指标。MNN VL 需 OMNI 构建,暂走 MLX |
| 文档扫描 | VisionKit `VNDocumentCameraView` | 不要自己写透视校正 |
| Face ID | LocalAuthentication | |