Local Ai

b8862

Release b8862 of llama.cpp includes a fix for 'mtmd: correct get_n_pos / get_decoder_pos' and provides compiled binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler

DGX agentgithub
local-aillama-cpp-releases

Release b8862 of llama.cpp includes a fix for "mtmd: correct get_n_pos / get_decoder_pos" and provides compiled binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler with various backend support options (CPU, GPU acceleration via CUDA, Vulkan, ROCm, and other optimizations). This release represents a typical incremental update in the llama.cpp project's continuous deployment model.

Related

Source: llama.cpp Releases | 2026-04-20

Loading related sources…