56 lines
1.2 KiB
YAML
56 lines
1.2 KiB
YAML
|
|
apiVersion: apps/v1
|
|||
|
|
kind: Deployment
|
|||
|
|
metadata:
|
|||
|
|
name: deepseekr10528-lb-main
|
|||
|
|
labels:
|
|||
|
|
app: deepseekr10528-lb
|
|||
|
|
spec:
|
|||
|
|
replicas: 1
|
|||
|
|
selector:
|
|||
|
|
matchLabels:
|
|||
|
|
app: deepseekr10528-lb
|
|||
|
|
template:
|
|||
|
|
metadata:
|
|||
|
|
labels:
|
|||
|
|
app: deepseekr10528-lb
|
|||
|
|
spec:
|
|||
|
|
nodeSelector:
|
|||
|
|
bo: "yes"
|
|||
|
|
tolerations:
|
|||
|
|
- key: bopd
|
|||
|
|
operator: Exists
|
|||
|
|
- key: node-role
|
|||
|
|
operator: Exists
|
|||
|
|
containers:
|
|||
|
|
- name: sgl-minilb
|
|||
|
|
image: lmsysorg/sglang:latest
|
|||
|
|
command:
|
|||
|
|
- python
|
|||
|
|
- -m
|
|||
|
|
- sglang.srt.disaggregation.mini_lb
|
|||
|
|
- --prefill
|
|||
|
|
- http://deepseekr10528-prefill-main:30000
|
|||
|
|
- --decode
|
|||
|
|
- http://deepseekr10528-decode-main:30000
|
|||
|
|
- --host
|
|||
|
|
- 0.0.0.0
|
|||
|
|
- --port
|
|||
|
|
- "8000"
|
|||
|
|
ports:
|
|||
|
|
- containerPort: 8000
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
apiVersion: v1
|
|||
|
|
kind: Service
|
|||
|
|
metadata:
|
|||
|
|
name: deepseekr10528-lb-service
|
|||
|
|
spec:
|
|||
|
|
type: NodePort # NodePort is easy to test, you can also specify `ClusterIP`
|
|||
|
|
selector:
|
|||
|
|
app: deepseekr10528-lb
|
|||
|
|
ports:
|
|||
|
|
- protocol: TCP
|
|||
|
|
port: 8000 # Service Port(In-Cluster)
|
|||
|
|
targetPort: 8000 # Exposed Container
|
|||
|
|
nodePort: 30800
|