Apple Core AI 框架
Apple 在 WWDC 上发布的本地 AI 框架,统一了 CPU、GPU、Neural Engine 的推理接口,做 iOS/macOS AI 应用的开发者必看,提前适配就能低成本用上设备端能力。
一篇关于 Apple Core AI 框架的 Hacker News 帖子获得 109 个点赞。帖子内容包含一张苹果开发者 OG 图片和一个指向 Apple Core AI Framework 官方文档的链接(developer.apple.com)。该帖子由 buzzing.cc 中文翻译,发布于 2026 年 6 月 8 日 02:47(UTC)。
Core AI | Apple Developer Documentation
Framework
Core AI
Run AI models in your app on Apple silicon.
iOS 27.0+Beta iPadOS 27.0+Beta Mac Catalyst 27.0+Beta macOS 27.0+Beta tvOS 27.0+Beta visionOS 27.0+Beta watchOS 27.0+Beta
Overview
Core AI helps you build, run, and deploy AI models in your app. Designed with Apple silicon in mind, Core AI allows your app to use the latest model architectures and inference techniques across the CPU, GPU, and Neural Engine. The Swift API makes common tasks simple, while giving you more control over model specialization, caching, and inference performance when needed.

Alongside the framework, Core AI includes additional tools for model preparation, integration, and debugging. Prepare your models for Apple silicon with Core AI Optimization, then convert them into the .aimodel format with Core AI PyTorch Extensions. The Core AI Debugger app supports visualization and numeric debugging, letting you inspect model structure and trace tensor values directly back to your Python source code.
Core AI also integrates with Xcode and the developer toolchain. The Core AI debug gauge and Core AI instrument help you monitor and profile inference performance in your app. You can also compile models ahead of time with the coreai-build command-line tool.
If your app uses model types other than neural networks, such as decision trees or tabular feature engineering, see Core ML.