Steal This: laya-mlx – Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text…

		Steal This: laya-mlx – Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text… (github.com/mizorewww)
		0 steals · 343 heat (6.9k stars on GitHub) 20 days ago \| clone this \| discuss
		Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API. spotted on GitHub

Nobody has copied this yet. Be the one.