Tag
vllm-swift 0.6.3 and longctx 0.3.2 releases bring triattentionv3 with 256k context on Apple Silicon, Gemma 4 MTP drafter support, Hermes tool calling with auto-recovery, and a longctx-svc daemon for scaling to 12M-token corpora.
This open-source Swift project provides a macOS driver for the Griffin PowerMate USB knob, enabling users to map rotation and button presses to system-wide scroll and click events. It includes a background agent and detailed technical documentation for USB HID interaction.
The author details the process of optimizing custom matrix multiplication kernels in Swift to train a Large Language Model on Apple Silicon, aiming to outperform C implementations by leveraging CPU, SIMD, AMX, and GPU capabilities.
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.
Developer shares the tech stack behind PACT, a social alarm mobile app featuring AI verification, real-time push notifications, and in-app payments, built natively in Swift.