#aarch64
AI
NUMALLAMA
NUMALLAMA is a lightweight C inference engine designed to run modern Large Language Models directly on CPUs — without GPUs, CUDA, or heavyweight runtime dependencies. Its primary goal is to make large multi-socket ARM se
Readme
Cross-compiling the Linux kernel
x86 → arm64 1. Dependencies (Debian/Ubuntu) 2. Sources Or a tarball from kernel.org: tar xf linux-6.12.tar.xz. 3. Environment variables Or pass them to every make call. This is more reliable: variables get lost when you
docs
documentation from markdown files
Updated Nov 19, 2026