llama.cpp Releases Automated Build b11130 with Internal Script Updates
llama.cpp has released automated build b11130, introducing a minor update to the summary prompt in its make-release script. The release provides newly compiled binary assets across multiple operating systems and hardware backends. This is a routine automated release containing no functional engine updates or performance changes for end users. It demonstrates the project's continuous integration pipeline, delivering regular pre-compiled binaries for developers and integration testing. The only commit included in this build updates the prompt used by internal scripts to generate release summaries. Additionally, the macOS Apple Silicon build with Arm KleidiAI integration remains explicitly disabled.
## BACKGROUND
llama.cpp is a high-performance open-source C/C++ LLM inference engine optimized for running models locally across diverse hardware, including CPUs, GPUs, and NPUs. Arm KleidiAI is an open-source library from Arm that provides optimized microkernels for accelerating AI workloads on Arm CPU architectures.