llama.cpp b10179 released with BoringSSL update and broad platform support
The latest llama.cpp release brings security upgrades and runs on virtually every platform.
Deep Dive
llama.cpp version b10179 was released by GitHub Actions on 29 July (no year specified). The update includes a vendor update to BoringSSL 0.20260728.0. Pre-built binaries are available for macOS (Apple Silicon, Intel), Linux (CPU, Vulkan, ROCm, OpenVINO, SYCL), Windows (CPU, CUDA, Vulkan, OpenCL, HIP), Android (arm64), and openEuler.
Key Points
- Updated BoringSSL to version 0.20260728.0 for improved security and performance.
- Supports 20+ build variants covering macOS, Linux, Windows, Android, and openEuler.
- Includes GPU backends like CUDA 12/13, ROCm 7.2, Vulkan, OpenCL, SYCL, and HIP.
Why It Matters
This release keeps the most popular local LLM engine secure and accessible across every major hardware platform.