kubectl-ai/modelserving/k8s/rpc-server-cuda.yaml at main · mikebz/kubectl-ai · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
kind: ServiceAccount
apiVersion: v1
metadata:
  name: rpc-server

---

kind: Service
apiVersion: v1
metadata:
  name: rpc-server
  labels:
    app: rpc-server
spec:
  clusterIP: None
  selector:
    app: rpc-server

---

kind: StatefulSet
apiVersion: apps/v1
metadata:
  name: rpc-server
spec:
  podManagementPolicy: "Parallel"
  replicas: 4
  selector:
    matchLabels:
      app: rpc-server
  serviceName: rpc-server
  template:
    metadata:
      labels:
        app: rpc-server
    spec:
      serviceAccountName: rpc-server
      containers:
      - name: rpc-server
        image: rpc-server-cuda:latest # placeholder value, replaced by deployment scripts
        args:
        - --host
        - 0.0.0.0
        resources:
          limits:
            nvidia.com/gpu: "1"
          requests:
            nvidia.com/gpu: "1"
      nodeSelector:
        cloud.google.com/gke-accelerator: nvidia-l4