Gluttony-Cluster/vllm/vllm-service.yaml

13 lines
209 B
YAML
Raw Normal View History

2024-03-31 02:25:35 +00:00
apiVersion: v1
kind: Service
metadata:
name: vllm-inference-server
namespace: vllm-ns
spec:
selector:
app: vllm-inference-server
type: LoadBalancer
ports:
- port: 8000
targetPort: http