AI/ML 온디바이스 2026.08.02 ⭐ 9/10

RunAnywhere

Hand-written GPU and NPU kernels for fast on-device inference across consumer silicon (Apple/Qualcomm)

온디바이스 AI 추론 (Apple/Qualcomm NPU 가속)

📰 관련 뉴스

Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon

Fastest LLM decode engine on Apple Silicon. 658 tok/s on M4-max, beats MLX by 19%

🔗 참고 링크

🌐 웹사이트 · RunAnywhere — Inference, from the metal up 💻 GitHub · RunanywhereAI/RCLI