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

guides-stack/llama-alpha.service

@@ -0,0 +1,32 @@
+[Unit]
+Description=llama.cpp server - alpha (meta/combat/action_eval on Ada #1)
+After=network-online.target
+
+[Service]
+Type=simple
+User=nyx-organs
+Group=nimmerverse-agents
+Environment="CUDA_VISIBLE_DEVICES=0"
+Environment="PATH=/usr/local/cuda/bin:/data/venvs/llama/bin:/usr/local/bin:/usr/bin:/usr/sbin:/bin"
+ExecStart=/data/llama.cpp/build/bin/llama-server \
+    --model /data/models/prod/alpha/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf \
+    --model-draft /data/models/prod/alpha/mtp-gemma-4-31B-it.gguf \
+    --spec-type draft-mtp \
+    -fa on \
+    --alias alpha \
+    --host 0.0.0.0 \
+    --port 31001 \
+    --n-gpu-layers 40 \
+    --ctx-size 65536 \
+    --cache-type-k q4_0 \
+    --cache-type-v q4_0 \
+    --batch-size 2048 \
+    --ubatch-size 512 \
+    --threads 8 \
+    --cont-batching \
+    --reasoning off
+RestartSec=5
+WorkingDirectory=/data
+
+[Install]
+WantedBy=multi-user.target