checkpoint commit

active/software_ai_stack/llama-code.container

@@ -0,0 +1,49 @@
+[Unit]
+Description=A Llama CPP Server Running a Coding Model
+
+[Container]
+# Shared AI internal pod without internet access
+Pod=ai-internal.pod
+
+# Image is built locally via podman build
+Image=localhost/llama-cpp-vulkan:latest
+
+# Downloaded models volume
+Volume=/home/ai/models/text:/models:z
+
+# GPU Device
+AddDevice=/dev/kfd
+AddDevice=/dev/dri
+
+# Server command
+Exec=--port 8003 \
+    -c 256000 \
+    -n 65536 \
+    --temp 0.7 \
+    --top-p 0.8 \
+    --top-k 20 \
+    --repeat-penalty 1.05 \
+    --perf \
+    --n-gpu-layers all \
+    --jinja \
+    -m /models/qwen3-coder-30b-a3b/Qwen3-Coder-30B-A3B-Instruct-Q5_K_M.gguf \
+    --alias code
+
+# Health Check
+HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8003/health || exit 1
+HealthInterval=10s
+HealthRetries=3
+HealthStartPeriod=10s
+HealthTimeout=30s
+HealthOnFailure=kill
+
+EnvironmentFile=/home/ai/.llama-api/keys.env
+
+[Service]
+Restart=always
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target