mizorewww/laya-mlx · AI Repo StatsMImizorewww/laya-mlx
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Suy luận & chạy LLM cục bộPython Apache-2.0 576tạo 2026-09-19 #apple-silicon#decision-model#inference#laya#local-ai#machine-learning#mlx#modernbert#system-one#typed-decisions