feat(AI): 集成MNN推理引擎替换MLX作为主AI运行时

- 引入MNN(alibaba) + Arm SME2 + CPU作为主AI运行时,支持A19/iPhone17的
  SME2和A17的NEON加速
- 添加MLX Swift作为兜底GPU推理方案,实现双后端切换机制
- 使用单一Qwen3.5-2B多模态模型(1.2GB),替代原有的LLM+VL分离架构
- 实现InferenceEngine.current引擎选择逻辑,真机默认MNN,模拟器回退MLX
- 更新AIAgent架构,通过MNNLLMBridge(ObjC++) → MNNBackend进行推理
- 修改队列机制防止并发推理导致OOM,使用信号量闸门控制显存占用
- 更新文档中的技术栈说明、模块边界和周次交付计划
```
This commit is contained in:
link2026
2026-06-15 09:24:59 +08:00
parent 6c6a950140
commit 9d856fcfc4
37 changed files with 2605 additions and 430 deletions

View File

@@ -0,0 +1,47 @@
import SwiftUI
/// Vault
///
/// body `try? FileVault.shared.loadImage(...)` + ,
/// :
/// 1. **OOM**:(4000×3000 48MB), jetsam `maxPixel`
/// , KB, MB
/// 2. **线**: + JPEG 线线,线
///
/// :,,
/// `content` `UIImage`( `Image`),
/// 便 `image.size` ( overlay)
struct VaultImage<Content: View, Placeholder: View>: View {
let relativePath: String
/// () ~400, ~2000
var maxPixel: CGFloat = 1024
@ViewBuilder var content: (UIImage) -> Content
/// ,`isLoading == true` ,`false`
@ViewBuilder var placeholder: (_ isLoading: Bool) -> Placeholder
@State private var image: UIImage?
@State private var loading = true
var body: some View {
Group {
if let image {
content(image)
} else {
placeholder(loading)
}
}
// id (TabView / asset);
.task(id: relativePath) {
loading = true
let path = relativePath
let mp = maxPixel
let loaded = await Task.detached(priority: .userInitiated) {
try? FileVault.shared.loadDownsampledImage(relativePath: path, maxPixelSize: mp)
}.value
guard !Task.isCancelled else { return }
image = loaded
loading = false
}
}
}