llama.cpp b11272 optimizes Hexagon NPU and adds CUDA 13

How it developed

1. September 30, 2026llama.cpp ReleasesWhere it started

   llama.cpp b11272 optimizes Hexagon NPU and adds CUDA 13

2. October 12, 2026llama.cpp Releases

   llama.cpp adds Hexagon IM2COL_3D support

   llama.cpp rewrites Hexagon IM2COL kernel to use canonical DMA double-buffer pipeline removing scalar FP16 conversions