- 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
36 lines
718 B
YAML
36 lines
718 B
YAML
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
|