Files
kangkang/康康/Services/BenchmarkService.swift

68 lines
2.6 KiB
Swift

import Foundation
/// ,MNN·SME2 vs MLX·GPU(§12 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
}
/// : prompt, AIRuntime , UserDefaults
/// UI(ModelSelfTestView) AIRuntime(§3.1)
@MainActor
struct BenchmarkService {
static let shared = BenchmarkService()
private init() {}
nonisolated static let storeKey = "kk.benchmark.results"
/// prompt:/
static let fixedPrompt = "用中文一句话介绍肝功能里 ALT 这个指标。"
/// onToken UI
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: - (,;nonisolated: UserDefaults ,线)
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
}
}