Popular repositories Loading

1. mlx2 mlx2 Public

   EXPERIMENTAL — research-grade MLX inference runtime for Apple Silicon (capability-routed serving, APCv2 prefix cache, speculative decoding). Unstable; not for production.

   Python 2

2. HorribleCanoe HorribleCanoe Public

   Forked from paralax/HorribleCanoe

   yara rules

   1

3. threatinator threatinator Public

   Forked from cikl/threatinator

   Ruby 1

4. NeuralKernel NeuralKernel Public

   An AI runtime that gets faster over time by compiling repeated neural work into verified deterministic code.

   Python 1

5. mlx-minimax-music3 mlx-minimax-music3 Public

   Apple-Silicon (MLX) port of MiniMaxAI/MiniMax-Music3 — on-device text-to-music

   Python 1

6. apple-silicon-inference-tuning apple-silicon-inference-tuning Public

   A measured field guide to serving LLMs fast on Apple Silicon (MLX-first).

   Python 1