68 lines
1.6 KiB
YAML
68 lines
1.6 KiB
YAML
apiVersion: apps/v1
|
|
kind: StatefulSet
|
|
metadata:
|
|
name: ollama
|
|
namespace: ai-core
|
|
labels:
|
|
app.kubernetes.io/name: ollama
|
|
app.kubernetes.io/component: llm-runtime
|
|
agentic-os.io/layer: ai-core
|
|
spec:
|
|
serviceName: ollama
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: ollama
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: ollama
|
|
agentic-os.io/layer: ai-core
|
|
spec:
|
|
securityContext:
|
|
fsGroup: 1000
|
|
containers:
|
|
- name: ollama
|
|
image: ollama/ollama:0.7.0
|
|
ports:
|
|
- containerPort: 11434
|
|
name: http
|
|
env:
|
|
- name: OLLAMA_HOST
|
|
value: "0.0.0.0"
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /api/tags
|
|
port: 11434
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 20
|
|
timeoutSeconds: 5
|
|
failureThreshold: 3
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /api/tags
|
|
port: 11434
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 10
|
|
timeoutSeconds: 5
|
|
failureThreshold: 3
|
|
resources:
|
|
requests:
|
|
cpu: "2"
|
|
memory: 4Gi
|
|
limits:
|
|
cpu: "8"
|
|
memory: 16Gi
|
|
volumeMounts:
|
|
- name: models
|
|
mountPath: /root/.ollama
|
|
volumeClaimTemplates:
|
|
- metadata:
|
|
name: models
|
|
spec:
|
|
storageClassName: longhorn
|
|
accessModes: ["ReadWriteOnce"]
|
|
resources:
|
|
requests:
|
|
storage: 50Gi
|