[Unit]
Description=llmgw node agent
After=network-online.target
Wants=network-online.target

[Service]
ExecStart=/usr/local/bin/llmgw agent --config /etc/llmgw/agent.yaml
# Root, because the agent launches engines and needs device access. Engines
# outlive a restart of this unit and are adopted again on the next start, so
# KillMode must not take the whole process group with it.
KillMode=process
Restart=on-failure
RestartSec=2s
# RDMA pins the buffers it registers, and NCCL registers a great deal: with
# systemd's default 8 MB lock limit, an engine that drops the capability that
# lets root ignore it fails its first collective over InfiniBand.
LimitMEMLOCK=infinity
StateDirectory=llmgw-agent

[Install]
WantedBy=multi-user.target