hmlb/clusters/homelab/apps/llm/vllm/granite-validation-debug.yaml at main · frzifus/hmlb · 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
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: model-validation-debug
  namespace: llm
  labels:
    app: model-validation-debug
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: model-validation-debug
  template:
    metadata:
      annotations:
        instrumentation.opentelemetry.io/inject-sdk: "true"
      labels:
        app: model-validation-debug
    spec:
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: "gpu.intel.com/device-id.0300-56a0.present"
                operator: "In"
                values:
                - "true"
      containers:
      - command: ["sleep", "36000"]
        image: ghcr.io/sigstore/model-transparency-cli:v1.1.1
        name: debug
        resources:
          requests:
            cpu: "50m"
            memory: "1Gi"
          limits:
            cpu: "1000m"
            memory: "2Gi"
        volumeMounts:
        - mountPath: /models
          name: hf-cache
      volumes:
      - name: hf-cache
        persistentVolumeClaim:
          claimName: model-cache