标签
SwiftLM is a Swift-native LLM inference server for Apple Silicon that runs large models without Python, using SSD streaming to load MoE weights and enabling 122B models on 64 GB Macs.
开发者公开社交闹钟 App「PACT」技术栈：AI 验证、实时推送、应用内支付，全部用 Swift 原生开发。