git clone https://github.com/ggml-org/llama.cpp ~/llama.cpp
cd ~/llama.cpp
git checkout 95ef7fc
cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=75 -DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release -j --target llama-server
ls build/bin/llama-server