llama.cpp b11037 fixes GPU inference bugs

How it developed

1. September 19, 2026llama.cpp ReleasesWhere it started

   llama.cpp b11037 fixes GPU inference bugs

2. September 28, 2026llama.cpp Releases

   llama.cpp fixes Vulkan inference bugs on strided KV caches

   llama.cpp fixes Vulkan bugs in strided KV cache matrix multiplication affecting Intel and NVIDIA hardware

3. October 2, 2026llama.cpp Releases

   llama.cpp b11339 fixes cache reallocation crash

   llama.cpp b11339 fixes a cache reallocation crash during full-context decoding by clamping re-pool bounds to existing pools