llama.cpp b11081 release with CUDA 13 and ROCm 10 support

How it developed

1. September 22, 2026llama.cpp ReleasesWhere it started

   llama.cpp b11081 release with CUDA 13 and ROCm 10 support

2. October 2, 2026llama.cpp Releases

   llama.cpp optimizes NVIDIA V100 inference performance

   llama.cpp adds a 3% throughput boost for NVIDIA V100 users by routing sm_70 to the Turing MMVQ nwarps table