84 lines
2.4 KiB
YAML
84 lines
2.4 KiB
YAML
|
|
apiVersion: batch/v1
|
|
kind: CronJob
|
|
metadata:
|
|
name: deepseek-analyst-v1.1
|
|
namespace: customer1
|
|
spec:
|
|
schedule: "15 * * * *"
|
|
jobTemplate:
|
|
spec:
|
|
template:
|
|
spec:
|
|
nodeSelector:
|
|
accelerator: "a100-80gb"
|
|
cloud.google.com/gke-accelerator: "nvidia-tesla-a100-80gb"
|
|
|
|
# 2. ACCEPT THE GPU TAINT
|
|
tolerations:
|
|
- key: "nvidia.com/gpu-a100-80gb"
|
|
operator: "Equal"
|
|
value: "present"
|
|
effect: "NoSchedule"
|
|
# Standard GPU toleration for GKE system
|
|
- key: "nvidia.com/gpu"
|
|
operator: "Exists"
|
|
effect: "NoSchedule"
|
|
|
|
volumes:
|
|
- name: deepseek-storage
|
|
persistentVolumeClaim:
|
|
claimName: deepseek-storage
|
|
|
|
|
|
initContainers:
|
|
- name: model-puller
|
|
image: ollama/ollama:latest
|
|
volumeMounts:
|
|
- name: deepseek-storage
|
|
mountPath: /root/.ollama
|
|
command: ["/bin/sh", "-c"]
|
|
args: ["ollama serve & sleep 5 && ollama pull deepseek-r1:70b"]
|
|
|
|
|
|
- name: ollama-sidecar
|
|
image: ollama/ollama:latest
|
|
restartPolicy: Always
|
|
env:
|
|
- name: OLLAMA_DEBUG
|
|
value: "2"
|
|
- name: OLLAMA_LOG_LEVEL
|
|
value: "DEBUG"
|
|
ports:
|
|
- containerPort: 11434
|
|
volumeMounts:
|
|
- name: deepseek-storage
|
|
mountPath: /root/.ollama
|
|
|
|
resources:
|
|
limits:
|
|
nvidia.com/gpu: "1"
|
|
memory: "90Gi"
|
|
requests:
|
|
nvidia.com/gpu: "1"
|
|
memory: "80Gi"
|
|
cpu: "10"
|
|
|
|
containers:
|
|
- name: analyst
|
|
image: siriussec/summarizerlocal:3.5
|
|
imagePullPolicy: Always
|
|
env:
|
|
- name: DB_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: news-app-password
|
|
key: password
|
|
envFrom:
|
|
- configMapRef:
|
|
name: deepseek-config
|
|
resources:
|
|
requests:
|
|
cpu: "2"
|
|
memory: "4Gi"
|
|
restartPolicy: OnFailure
|