LocalAI/examples/kubernetes/deployment-intel-arc.yaml
Ettore Di Giacinto 53dbe36f32
feat(tts): respect YAMLs config file, add sycl docs/examples (#1692)
* feat(refactor): refactor config and input reading

* feat(tts): read config file for TTS

* examples(kubernetes): Add simple deployment example

* examples(kubernetes): Add simple deployment for intel arc

* docs(sycl): add sycl example

* feat(tts): do not always pick a first model

* fixups to run vall-e-x on container

* Correctly resolve backend
2024-02-10 21:37:03 +01:00

68 lines
1.2 KiB
YAML

apiVersion: v1
kind: Namespace
metadata:
name: local-ai
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: models-pvc
namespace: local-ai
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 20Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: local-ai
namespace: local-ai
labels:
app: local-ai
spec:
selector:
matchLabels:
app: local-ai
replicas: 1
template:
metadata:
labels:
app: local-ai
name: local-ai
spec:
containers:
- args:
- phi-2
env:
- name: DEBUG
value: "true"
name: local-ai
image: quay.io/go-skynet/local-ai:master-sycl-f32-ffmpeg-core
imagePullPolicy: Always
resources:
limits:
gpu.intel.com/i915: 1
volumeMounts:
- name: models-volume
mountPath: /build/models
volumes:
- name: models-volume
persistentVolumeClaim:
claimName: models-pvc
---
apiVersion: v1
kind: Service
metadata:
name: local-ai
namespace: local-ai
spec:
selector:
app: local-ai
type: LoadBalancer
ports:
- protocol: TCP
port: 8080
targetPort: 8080