Local Ai
b9578
Release b9578 of llama.cpp includes a refactor of video subprocess handling in the mtmd (multi-threaded multi-device) component via pull request #24316 . The release provides prebuilt binaries across
Release b9578 of llama.cpp includes a refactor of video subprocess handling in the mtmd (multi-threaded multi-device) component via pull request #24316 . The release provides prebuilt binaries across multiple platforms including macOS, Linux, Android, Windows, and other architectures with support for various hardware accelerators including CUDA, Vulkan, ROCm, and Metal frameworks.
Source: llama.cpp Releases | 2026-06-09