[Unit]
Description=Ollama+Anthropic API proxy backed by llama.cpp (Qwen3.8-27B)
Documentation=file:///opt/llama-server/USAGE-CLIENTS.md
After=network-online.target llama-server.service
Wants=network-online.target

[Service]
Type=simple
ExecStart=/usr/bin/python3 /opt/llama-server/ollama-proxy.py
Restart=on-failure
RestartSec=5
TimeoutStopSec=30
# proxy does not need GPU access itself; it forwards to llama-server on 127.0.0.1:8080
NoNewPrivileges=true
PrivateTmp=true
LimitNOFILE=1048576

[Install]
WantedBy=multi-user.target