new llamacpp service

llamacpp/pv.yaml

@@ -0,0 +1,47 @@
+# Shared model-weight storage for all llama.cpp pods.
+#
+# All llamacpp pods are pinned to the NUCBox (roger-nucbox-evo-x2) via
+# nodeSelector, so a single hostPath PV on that node is correct and matches the
+# existing postgres hostPath pattern. GGUF files are large (10s of GB); baking
+# them into images would be wasteful, and an initContainer downloads them
+# idempotently on first boot instead.
+#
+# nodeAffinity keeps the PV bound to the NUCBox even if labels change later.
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: llamacpp-models
+  labels:
+    type: local
+    app: llamacpp
+spec:
+  storageClassName: manual
+  capacity:
+    storage: 100Gi
+  accessModes:
+    - ReadWriteMany
+  hostPath:
+    path: /data/llamacpp/models
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+        - matchExpressions:
+            - key: kubernetes.io/hostname
+              operator: In
+              values:
+                - roger-nucbox-evo-x2
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: llamacpp-models
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+spec:
+  storageClassName: manual
+  accessModes:
+    - ReadWriteMany
+  resources:
+    requests:
+      storage: 100Gi