The ggml‑org team released llama.cpp version b11789. The update adds dp4a GEMM (matrix‑multiply) variants for OpenCL with vector activation loads, and renames related kernels and environment variables. Pre‑built binaries are now available for Apple Silicon, Intel macOS, iOS, and several Ubuntu builds (CPU, Vulkan, CUDA). The changes are aimed at improving performance on GPUs that support the dp4a instruction.
Why it matters
Developers can run llama.cpp faster on compatible GPUs, reducing inference time for local LLM applications.
