[Unit]
Description=llama.cpp OpenAI-compatible server (Qwen3.8-27B Q4_K_P, 3x Turing GPUs, 256K ctx)
Documentation=file:///opt/llama-server/README.md
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
# Required: without this the loader binds a stale libcuda.so.1 (550) from
# /usr/lib/x86_64-linux-gnu/nvidia/current and CUDA init fails with
# "system has unsupported display driver / cuda driver combination".
Environment=LD_LIBRARY_PATH=/opt/llama.cpp/build-nccl/bin:/opt/minicpm-venv/lib/python3.13/site-packages/nvidia/nccl/lib:/lib/x86_64-linux-gnu
ExecStart=/opt/llama-server/start.sh
Restart=on-failure
RestartSec=10
# Model load takes ~20s; give it time to come up cleanly
TimeoutStartSec=300
TimeoutStopSec=60
# Basic hardening (server only listens on :8080, reads models read-only)
ProtectSystem=strict
ProtectHome=read-only
ReadWritePaths=/var/cache/llama-slots /tmp
NoNewPrivileges=true
PrivateTmp=true
# Do not cap memory/CPU; inference needs all of it
LimitNOFILE=1048576
# NUMA Affinity: Pin to CPU Socket 1 (NUMA Node 1) where Riser 1 GPUs physically connect (24-thread v2 CPU)
CPUAffinity=6-11,18-23
NUMAPolicy=bind
NUMAMask=1

[Install]
WantedBy=multi-user.target