feat: vLLM in K8s via Harbor mirror, pipelines point to internal svc

- vLLM image mirrored to registry.celestium.life/stonks-oracle/vllm-openai
- Deployment uses Harbor image (Docker Hub IPv6 unreachable from cluster)
- All 3 pipelines use vllm-external.vllm-service.svc.cluster.local:2701
- K8s manifests at infra/kube-vllm/ and synced to ~/sources/kube/vllm

infra/kube-vllm/storage.yaml

@@ -0,0 +1,35 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: vllm-hf-cache-pv
+spec:
+  capacity:
+    storage: 50Gi
+  accessModes:
+    - ReadWriteOnce
+  persistentVolumeReclaimPolicy: Retain
+  storageClassName: local-path
+  hostPath:
+    path: /var/lib/vllm/hf-cache
+    type: DirectoryOrCreate
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+        - matchExpressions:
+            - key: kubernetes.io/hostname
+              operator: In
+              values:
+                - gremlin-1
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: vllm-hf-cache-pvc
+  namespace: vllm-service
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 50Gi
+  storageClassName: local-path