feat(Me): 性能自检卡 — 后端标识 + prefill/decode 实测 + 引擎对比存档

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

康康/Features/Me/ModelManagementView.swift

@@ -28,13 +28,13 @@ struct ModelManagementView: View {
                 actionButtons
                     .padding(.top, 4)
 
-                if service.states[.mnnLLM]?.phase == .ready {
+                if service.states[.mnnLLM]?.phase == .ready || service.states[.llm]?.phase == .ready {
                     NavigationLink {
                         ModelSelfTestView()
                     } label: {
                         HStack(spacing: 6) {
-                            Image(systemName: "play.circle")
+                            Image(systemName: "gauge.with.needle")
-                            Text("运行推理自检")
+                            Text("性能自检")
                         }
                         .frame(maxWidth: .infinity)
                     }

康康/Features/Me/ModelSelfTestView.swift

@@ -1,11 +1,13 @@
 import SwiftUI
 
-/// 模型推理自检:加载 LLM 跑一段固定 prompt,流式显示输出 + tok/s。
+/// 性能自检:跑固定 prompt,展示当前后端(MNN·SME2 / MNN·NEON / MLX·GPU)的
-/// 模型就绪后从「我的 · 模型管理」进入,用于现场快速验证本地推理是否正常。
+/// prefill / decode 实测速度,并按后端存档对比 —— 挑战赛考核点的可见证据(§12 卖点 2/6)。
 struct ModelSelfTestView: View {
     @State private var output = ""
     @State private var phase: Phase = .idle
     @State private var rate: Double = 0
+    @State private var lastResult: BenchmarkResult?
+    @State private var history: [String: BenchmarkResult] = [:]
 
     private enum Phase: Equatable {
         case idle, loading, running, done, failed(String)
@@ -21,8 +23,6 @@ struct ModelSelfTestView: View {
         }
     }
 
-    private let prompt = "用中文一句话介绍肝功能里 ALT 这个指标。"
-
     private var isBusy: Bool { phase == .loading || phase == .running }
 
     private var statusColor: Color {
@@ -34,79 +34,162 @@ struct ModelSelfTestView: View {
     }
 
     var body: some View {
-        VStack(alignment: .leading, spacing: 16) {
+        ScrollView {
-            VStack(alignment: .leading, spacing: 6) {
+            VStack(alignment: .leading, spacing: 16) {
-                Text("测试 PROMPT")
+                promptCard
-                    .font(.tjScaled( 11, weight: .semibold))
-                    .tracking(0.5)
-                    .foregroundStyle(Tj.Palette.text3)
-                Text(prompt)
-                    .font(.tjScaled( 14))
-                    .foregroundStyle(Tj.Palette.text)
-            }
-            .padding(14)
-            .frame(maxWidth: .infinity, alignment: .leading)
-            .tjCard()
 
+                HStack {
+                    Text(phase.label)
+                        .font(.tjScaled( 13, weight: .medium))
+                        .foregroundStyle(statusColor)
+                        .lineLimit(1)
+                    Spacer()
+                    if rate > 0 {
+                        Text(String(format: "%.1f tok/s", rate))
+                            .font(.tjScaled( 12, design: .monospaced))
+                            .foregroundStyle(Tj.Palette.text3)
+                    }
+                }
+
+                Button {
+                    Task { await run() }
+                } label: {
+                    Text(isBusy ? "运行中…" : "运行性能自检").frame(maxWidth: .infinity)
+                }
+                .buttonStyle(TjPrimaryButton())
+                .disabled(isBusy)
+
+                if isBusy { AIFlowBar() }
+
+                if let r = lastResult { statsCard(r) }
+
+                outputCard
+
+                if !history.isEmpty { historyCard }
+            }
+            .padding(16)
+        }
+        .background(Tj.Palette.sand.ignoresSafeArea())
+        .navigationTitle("性能自检")
+        .navigationBarTitleDisplayMode(.inline)
+        .onAppear { history = BenchmarkService.load() }
+    }
+
+    private var promptCard: some View {
+        VStack(alignment: .leading, spacing: 6) {
+            Text("测试 PROMPT")
+                .font(.tjScaled( 11, weight: .semibold))
+                .tracking(0.5)
+                .foregroundStyle(Tj.Palette.text3)
+            Text(BenchmarkService.fixedPrompt)
+                .font(.tjScaled( 14))
+                .foregroundStyle(Tj.Palette.text)
+        }
+        .padding(14)
+        .frame(maxWidth: .infinity, alignment: .leading)
+        .tjCard()
+    }
+
+    private func statsCard(_ r: BenchmarkResult) -> some View {
+        VStack(alignment: .leading, spacing: 10) {
             HStack {
-                Text(phase.label)
+                Text("本次结果")
-                    .font(.tjScaled( 13, weight: .medium))
+                    .font(.tjScaled( 12, weight: .semibold))
-                    .foregroundStyle(statusColor)
+                    .foregroundStyle(Tj.Palette.text2)
-                    .lineLimit(1)
                 Spacer()
-                if rate > 0 {
+                TjBadge(text: r.backendLabel, style: .leaf)
-                    Text(String(format: "%.1f tok/s", rate))
+            }
-                        .font(.tjScaled( 12, design: .monospaced))
+            HStack(spacing: 0) {
-                        .foregroundStyle(Tj.Palette.text3)
+                metric(String(appLoc: "读入"), r.prefillTokensPerSecond > 0
+                       ? String(format: "%.0f tok/s", r.prefillTokensPerSecond) : "—")
+                metric(String(appLoc: "生成"), String(format: "%.1f tok/s", r.decodeTokensPerSecond))
+                metric(String(appLoc: "总耗时"), String(format: "%.1fs", r.totalSeconds))
+            }
+            Text(String(appLoc: "prompt \(r.promptTokens) tok · 生成 \(r.genTokens) tok · 100% 本地"))
+                .font(.tjScaled( 10, design: .monospaced))
+                .foregroundStyle(Tj.Palette.text3)
+        }
+        .padding(14)
+        .frame(maxWidth: .infinity, alignment: .leading)
+        .tjCard()
+    }
+
+    private func metric(_ label: String, _ value: String) -> some View {
+        VStack(spacing: 3) {
+            Text(value)
+                .font(.tjScaled( 15, weight: .semibold, design: .monospaced))
+                .foregroundStyle(Tj.Palette.text)
+            Text(label)
+                .font(.tjScaled( 10))
+                .foregroundStyle(Tj.Palette.text3)
+        }
+        .frame(maxWidth: .infinity)
+    }
+
+    private var outputCard: some View {
+        ScrollView {
+            Text(output.isEmpty ? "(暂无输出)" : output)
+                .font(.system(.footnote, design: .monospaced))
+                .foregroundStyle(Tj.Palette.text)
+                .frame(maxWidth: .infinity, alignment: .leading)
+                .textSelection(.enabled)
+                .padding(12)
+        }
+        .frame(maxHeight: 220)
+        .background(
+            RoundedRectangle(cornerRadius: Tj.Radius.md, style: .continuous)
+                .fill(Tj.Palette.paper)
+        )
+        .overlay(
+            RoundedRectangle(cornerRadius: Tj.Radius.md, style: .continuous)
+                .strokeBorder(Tj.Palette.lineSoft, lineWidth: 1)
+        )
+    }
+
+    private var historyCard: some View {
+        VStack(alignment: .leading, spacing: 10) {
+            Text("各引擎实测对比")
+                .font(.tjScaled( 12, weight: .semibold))
+                .foregroundStyle(Tj.Palette.text2)
+            ForEach(history.keys.sorted(), id: \.self) { key in
+                if let r = history[key] {
+                    HStack {
+                        Text(key)
+                            .font(.tjScaled( 12, weight: .medium))
+                            .foregroundStyle(Tj.Palette.text)
+                        Spacer()
+                        Text(String(format: String(appLoc: "生成 %.1f tok/s"), r.decodeTokensPerSecond))
+                            .font(.tjScaled( 12, design: .monospaced))
+                            .foregroundStyle(Tj.Palette.leaf)
+                        Text(r.date.formatted(.dateTime.month().day()))
+                            .font(.tjScaled( 10))
+                            .foregroundStyle(Tj.Palette.text3)
+                    }
                 }
             }
-
+            Text("在「我的 · 推理引擎」切换引擎后再跑一次,即可对比 SME2 与 GPU。")
-            Button {
+                .font(.tjScaled( 10))
-                Task { await run() }
+                .foregroundStyle(Tj.Palette.text3)
-            } label: {
-                Text(isBusy ? "运行中…" : "运行推理自检").frame(maxWidth: .infinity)
-            }
-            .buttonStyle(TjPrimaryButton())
-            .disabled(isBusy)
-
-            ScrollView {
-                Text(output.isEmpty ? "(暂无输出)" : output)
-                    .font(.system(.footnote, design: .monospaced))
-                    .foregroundStyle(Tj.Palette.text)
-                    .frame(maxWidth: .infinity, alignment: .leading)
-                    .textSelection(.enabled)
-                    .padding(12)
-            }
-            .frame(maxHeight: 280)
-            .background(
-                RoundedRectangle(cornerRadius: Tj.Radius.md, style: .continuous)
-                    .fill(Tj.Palette.paper)
-            )
-            .overlay(
-                RoundedRectangle(cornerRadius: Tj.Radius.md, style: .continuous)
-                    .strokeBorder(Tj.Palette.lineSoft, lineWidth: 1)
-            )
-
-            Spacer()
         }
-        .padding(16)
+        .padding(14)
-        .background(Tj.Palette.sand.ignoresSafeArea())
+        .frame(maxWidth: .infinity, alignment: .leading)
-        .navigationTitle("推理自检")
+        .tjCard()
-        .navigationBarTitleDisplayMode(.inline)
     }
 
     @MainActor
     private func run() async {
         output = ""
         rate = 0
+        lastResult = nil
         phase = .loading
         do {
-            try await AIRuntime.shared.prepare()
+            let result = try await BenchmarkService.shared.run { piece, r in
-            phase = .running
+                output += piece
-            for try await chunk in await AIRuntime.shared.generate(prompt: prompt, maxTokens: 200) {
+                if r > 0 { rate = r }
-                output += chunk.text
+                if phase == .loading { phase = .running }
-                rate = chunk.decodeRate
             }
+            lastResult = result
+            history = BenchmarkService.load()
             phase = .done
         } catch {
             phase = .failed(error.localizedDescription)

康康/Services/BenchmarkService.swift

@@ -0,0 +1,67 @@
+import Foundation
+
+/// 单次性能自检结果。按后端标签归档,供「MNN·SME2 vs MLX·GPU」对比展示(§12 卖点 2/6)。
+struct BenchmarkResult: Codable, Equatable {
+    var backendLabel: String
+    var promptTokens: Int
+    var genTokens: Int
+    var prefillTokensPerSecond: Double
+    var decodeTokensPerSecond: Double
+    var totalSeconds: Double
+    var date: Date
+}
+
+/// 性能自检服务:跑固定 prompt,取 AIRuntime 的归一统计,按后端标签存 UserDefaults。
+/// UI(ModelSelfTestView)只经本服务调 AIRuntime(§3.1)。
+@MainActor
+struct BenchmarkService {
+    static let shared = BenchmarkService()
+    private init() {}
+
+    nonisolated static let storeKey = "kk.benchmark.results"
+
+    /// 固定测试 prompt:跨设备/引擎可比的前提。
+    static let fixedPrompt = "用中文一句话介绍肝功能里 ALT 这个指标。"
+
+    /// 跑一次自检。onToken 把流式输出交给 UI 展示。
+    func run(onToken: @escaping @MainActor (String, Double) -> Void) async throws -> BenchmarkResult {
+        try await AIRuntime.shared.prepare()
+        let start = Date()
+        let stream = await AIRuntime.shared.generate(prompt: Self.fixedPrompt, maxTokens: 128)
+        for try await chunk in stream {
+            onToken(chunk.text, chunk.decodeRate)
+        }
+        let total = Date().timeIntervalSince(start)
+        let label = await AIRuntime.shared.activeBackendLabel
+        let stats = await AIRuntime.shared.lastGenerateStats
+        let result = BenchmarkResult(
+            backendLabel: label,
+            promptTokens: stats?.promptTokens ?? 0,
+            genTokens: stats?.genTokens ?? 0,
+            prefillTokensPerSecond: stats?.prefillTokensPerSecond ?? 0,
+            decodeTokensPerSecond: stats?.decodeTokensPerSecond ?? 0,
+            totalSeconds: total,
+            date: .now
+        )
+        Self.save(result)
+        return result
+    }
+
+    // MARK: - 存档(静态纯函数,单测覆盖;nonisolated:纯 UserDefaults 操作,无需主线程)
+
+    nonisolated static func save(_ result: BenchmarkResult, defaults: UserDefaults = .standard) {
+        var all = load(defaults: defaults)
+        all[result.backendLabel] = result
+        if let data = try? JSONEncoder().encode(all) {
+            defaults.set(data, forKey: storeKey)
+        }
+    }
+
+    nonisolated static func load(defaults: UserDefaults = .standard) -> [String: BenchmarkResult] {
+        guard let data = defaults.data(forKey: storeKey),
+              let all = try? JSONDecoder().decode([String: BenchmarkResult].self, from: data) else {
+            return [:]
+        }
+        return all
+    }
+}

康康Tests/BenchmarkStoreTests.swift

@@ -0,0 +1,45 @@
+import Testing
+import Foundation
+@testable import 康康
+
+struct BenchmarkStoreTests {
+
+    /// 每个用例独立 suite,避免 Swift Testing 并行执行时互相清空数据。
+    private func freshDefaults(_ name: String) -> UserDefaults {
+        let suite = "test.kk.benchmark.\(name)"
+        let d = UserDefaults(suiteName: suite)!
+        d.removePersistentDomain(forName: suite)
+        return d
+    }
+
+    @Test func savesAndLoadsPerBackend() {
+        let d = freshDefaults("savesAndLoads")
+        let mnn = BenchmarkResult(backendLabel: "MNN · SME2", promptTokens: 30, genTokens: 80,
+                                  prefillTokensPerSecond: 120, decodeTokensPerSecond: 25,
+                                  totalSeconds: 4.2, date: .now)
+        let mlx = BenchmarkResult(backendLabel: "MLX · GPU", promptTokens: 30, genTokens: 80,
+                                  prefillTokensPerSecond: 300, decodeTokensPerSecond: 40,
+                                  totalSeconds: 2.5, date: .now)
+        BenchmarkService.save(mnn, defaults: d)
+        BenchmarkService.save(mlx, defaults: d)
+        let all = BenchmarkService.load(defaults: d)
+        #expect(all.count == 2)
+        #expect(all["MNN · SME2"]?.decodeTokensPerSecond == 25)
+    }
+
+    @Test func overwritesSameBackend() {
+        let d = freshDefaults("overwrites")
+        let old = BenchmarkResult(backendLabel: "MLX · GPU", promptTokens: 1, genTokens: 1,
+                                  prefillTokensPerSecond: 1, decodeTokensPerSecond: 1,
+                                  totalSeconds: 1, date: .now)
+        var new = old
+        new.decodeTokensPerSecond = 99
+        BenchmarkService.save(old, defaults: d)
+        BenchmarkService.save(new, defaults: d)
+        #expect(BenchmarkService.load(defaults: d)["MLX · GPU"]?.decodeTokensPerSecond == 99)
+    }
+
+    @Test func loadOnEmptyReturnsEmpty() {
+        #expect(BenchmarkService.load(defaults: freshDefaults("loadEmpty")).isEmpty)
+    }
+}