Snap package for llama.cpp - LLM inference in C/C++
llama.cpp packaged as a snap. The main snap ships a CPU build that
works on any x86_64 or arm64 machine. Optional snap components add
GPU backends:
sudo snap install --edge --devmode llama-cpp # CPU
sudo snap install --edge --devmode llama-cpp+hip # add AMD GPU
sudo snap install --edge --devmode llama-cpp+cuda # add NVIDIA GPU
Select a backend persistently with:
sudo snap set llama-cpp backend={cpu,hip,cuda,auto} # auto = probe
snap get llama-cpp backend
or override it per invocation with the env var:
LLAMA_CPP_BACKEND=cpu llama-cpp cli ...