reconfigure software ai stack

active/software_ai_stack/llama-instruct.container

@@ -0,0 +1,51 @@
+[Unit]
+Description=A Llama CPP Server Running GPT OSS 120b
+
+[Container]
+# Shared AI internal pod
+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 8002 \
+    -c 16000 \
+    --perf \
+    -v \
+    --top-k 20 \
+    --top-p 0.8 \
+    --min-p 0 \
+    --presence-penalty 1.5 \
+    --repeat-penalty 1 \
+    --temp 0.7 \
+    --n-gpu-layers all \
+    --jinja \
+    --chat-template-kwargs '{"enable_thinking": false}' \
+    -m /models/qwen3.5-35b-a3b/Qwen3.5-35B-A3B-Q8_0.gguf \
+    --mmproj /models/qwen3.5-35b-a3b/mmproj-F16.gguf \
+    --alias instruct
+
+# Health Check
+HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8000/health || exit 1
+HealthInterval=10s
+HealthRetries=3
+HealthStartPeriod=10s
+HealthTimeout=30s
+HealthOnFailure=kill
+
+[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