[Unit]
Description=LLMSProxy - unified OpenAI-compatible multi-source LLM gateway
After=network.target

[Service]
Type=simple
# Memory tuning (measured, see README "内存占用"):
#   MALLOC_ARENA_MAX=2 caps glibc per-thread malloc arenas. LuaJIT allocates
#     through cgo -> glibc malloc, and glibc defaults to 8*nproc arenas, so every
#     OS thread that touches malloc reserved its own ~1 MB arena that is never
#     returned. Measured: 8-12 arenas -> 0.
#   GOGC=50 halves the Go heap growth target. On its own it does NOT help (the
#     saved heap is immediately eaten by more glibc arenas); combined with
#     MALLOC_ARENA_MAX it cut settled RSS by ~19%. This gateway is I/O bound, so
#     the extra GC cycles are free.
Environment=GOGC=50
Environment=MALLOC_ARENA_MAX=2
ExecStart=/usr/bin/llmsproxy -config /etc/llmsproxy/config.yaml
WorkingDirectory=/etc/llmsproxy
Restart=always
RestartSec=5

[Install]
WantedBy=multi-user.target