llama-cpp: LLM inference in C/C++1

The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.

... part of T2, get it here

URL: https://github.com/ggerganov/llama.cpp

Author: llama-cpp Authors
Maintainer: René Rebe <rene [at] exactco [dot] de>

License: MIT
Version: b8606

Download: https://github.com/ggerganov/ llama.cpp.git b8606llama-cpp-b8606.tar.gz

T2 source: llama-cpp.cache
T2 source: llama-cpp.desc
T2 source: opencl-amd.patch

Build time (on reference hardware): 540% (relative to binutils)2

Installed size (on reference hardware): 377.64 MB, 160 files

Dependencies (build time detected): bash binutils cmake coreutils diffutils findutils gawk grep gzip linux-header make openssl pkgconfig python sed tar util-linux

Installed files (on reference hardware): [show]

1) This page was automatically generated from the T2 package source. Corrections, such as dead links, URL changes or typos need to be performed directly on that source.

2) Compatible with Linux From Scratch's "Standard Build Unit" (SBU).