llama.cpp b11381 release with CUDA 13 and ROCm 10

How it developed

1. October 4, 2026llama.cpp ReleasesWhere it started

   llama.cpp b11381 release with CUDA 13 and ROCm 10

2. October 6, 2026llama.cpp Releases

   llama.cpp fixes OpenVINO GPU regressions and CI

   llama.cpp patches critical stability issues in its OpenVINO backend, fixing stateful inference crashes on CPU and GPU.