Files
klaster/apps/llama/deployment.yaml

79 lines
1.7 KiB
YAML

---
apiVersion: apps/v1
kind: Deployment
metadata:
name: llama-swap
namespace: llama
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app: llama-swap
template:
metadata:
labels:
app: llama-swap
spec:
containers:
- name: llama-swap
image: ghcr.io/mostlygeek/llama-swap:v199-vulkan-b8576
imagePullPolicy: IfNotPresent
command:
- /app/llama-swap
args:
- --config=/config/config.yaml
- --watch-config
ports:
- containerPort: 8080
name: http
protocol: TCP
env:
- name: OPENROUTER_API_KEY
valueFrom:
secretKeyRef:
name: llama-openrouter
key: OPENROUTER_API_KEY
volumeMounts:
- name: models
mountPath: /root/.cache
- mountPath: /dev/kfd
name: kfd
- mountPath: /dev/dri
name: dri
- mountPath: /config
name: config
securityContext:
privileged: true
volumes:
- name: models
persistentVolumeClaim:
claimName: llama-models-lvmssd
- name: kfd
hostPath:
path: /dev/kfd
type: CharDevice
- name: dri
hostPath:
path: /dev/dri
type: Directory
- name: config
configMap:
name: llama-swap
---
apiVersion: v1
kind: Service
metadata:
name: llama
namespace: llama
spec:
type: ClusterIP
ports:
- name: http
port: 11434
targetPort: 8080
protocol: TCP
selector:
app: llama-swap