Popular repositories Loading

1. turboQuantPlayground turboQuantPlayground Public

   TurboQuant (ICLR 2026) ported to Apple Silicon — KV cache compression with MLX Metal kernels + PyTorch CPU

   Python 2

2. mlx-turboquant mlx-turboquant Public

   TurboQuant KV cache compression for MLX-LM — run longer contexts on Apple Silicon with 5x less memory

   Python 2

3. turboquant-bench turboquant-bench Public

   Compare LLM inference with and without TurboQuant KV cache compression on Apple Silicon

   Python 1

4. SodukuSolver SodukuSolver Public

   VS2010 SodukuSolver project

5. SodukuSolver_vs2010 SodukuSolver_vs2010 Public

   SodukuSolver Visual Studio 2010 solution

   C++

6. FasterAnimationsContainer FasterAnimationsContainer Public

   Forked from tigerjj/FasterAnimationsContainer

   Frame Animation with Drawable without OutOfMemory

   Java