- 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
30 lines
503 B
YAML
30 lines
503 B
YAML
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: vllm
|
|
namespace: vllm-service
|
|
spec:
|
|
ports:
|
|
- name: http
|
|
port: 8000
|
|
targetPort: 8000
|
|
selector:
|
|
app: vllm
|
|
type: ClusterIP
|
|
---
|
|
# External access via NodePort (like ollama's port 2701 pattern)
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: vllm-external
|
|
namespace: vllm-service
|
|
spec:
|
|
ports:
|
|
- nodePort: 31508
|
|
name: vllm-api
|
|
port: 2701
|
|
targetPort: 8000
|
|
selector:
|
|
app: vllm-metrics
|
|
type: LoadBalancer
|