b9556

llama.cpp b9556 release adds support for AMD RDNA3.5 graphics hardware (gfx1152 and gfx1153) in its HIP backend . The release includes compiled binaries for multiple platforms including macOS, Linux, Android, and Windows with various acceleration backends (CUDA, Vulkan, ROCm, SYCL, and OpenVINO). llama.cpp is a C/C++ implementation for running large language model inference on consumer hardware with minimal dependencies.

Source: llama.cpp Releases | 2026-06-08