This content is still in French

The page itself is translated, but its detailed content is not yet. Hardware sheets, guides and catalogues are still shown in French: we would rather give you the original than a rough machine translation. View the French site

Compiler llama.cpp pour tirer le maximum du processeur Étape 7 sur 7

Installer en service

Pour que le serveur redémarre avec la machine :

shell

sudo tee /etc/systemd/system/llama.service >/dev/null <<'EOF'
[Unit]
Description=llama.cpp server
After=network.target

[Service]
User=pi
WorkingDirectory=/home/pi/llama.cpp
ExecStart=/home/pi/llama.cpp/build/bin/llama-server -m /home/pi/modeles/Qwen3-4B-Q4_K_M.gguf -c 4096 -t 4 --host 0.0.0.0 --port 8080
Restart=always
RestartSec=5

[Install]
WantedBy=multi-user.target
EOF

sudo systemctl daemon-reload
sudo systemctl enable --now llama
systemctl status llama

Adaptez User et les chemins à votre installation.