new service files - updates to ll-stack-architecture.md

guides-stack/llama-zeta.service

@@ -0,0 +1,23 @@
+[Unit]
+Description=llama.cpp server - zeta
+After=network-online.target
+
+[Service]
+Type=simple
+User=nyx-organs
+Group=nimmerverse-agents
+Environment="PATH=/usr/local/cuda/bin:/data/venvs/llama/bin:/usr/local/bin:/usr/bin:/usr/sbin:/bin"
+ExecStart=llama-server \
+    --model /data/models/prod/zeta/Huihui-Qwen3-VL-8B-Instruct-abliterated.Q8_0.gguf \
+    --alias zeta \
+    --mmproj /data/models/prod/zeta/zeta-mmproj-Q8_0.gguf \
+    --host 0.0.0.0 \
+    --port 31003 \
+    --n-gpu-layers 9999 \
+    --ctx-size 64000 \
+    --chat-template-kwargs '{"enable_thinking": false}'
+RestartSec=5
+WorkingDirectory=/data
+
+[Install]
+WantedBy=multi-user.target