40 lines
1005 B
YAML
40 lines
1005 B
YAML
|
apiVersion: apps/v1
|
||
|
|
kind: Deployment
|
||
|
|
metadata:
|
||
|
|
name: server
|
||
|
|
labels:
|
||
|
|
app.kubernetes.io/component: server
|
||
|
|
spec:
|
||
|
|
replicas: 1
|
||
|
|
strategy:
|
||
|
|
type: Recreate
|
||
|
|
selector:
|
||
|
|
matchLabels:
|
||
|
|
app.kubernetes.io/component: server
|
||
|
|
template:
|
||
|
|
metadata:
|
||
|
|
labels:
|
||
|
|
app.kubernetes.io/component: server
|
||
|
|
spec:
|
||
|
|
affinity:
|
||
|
|
nodeAffinity:
|
||
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
||
|
|
nodeSelectorTerms:
|
||
|
|
- matchExpressions:
|
||
|
|
# Image only supports amd64
|
||
|
|
- key: kubernetes.io/arch
|
||
|
|
operator: In
|
||
|
|
values:
|
||
|
|
- amd64
|
||
|
|
runtimeClassName: nvidia
|
||
|
|
containers:
|
||
|
|
- name: kokoro-tts
|
||
|
|
image: ghcr.io/remsky/kokoro-fastapi-gpu:v0.1.4
|
||
|
|
resources:
|
||
|
|
requests:
|
||
|
|
cpu: 500m
|
||
|
|
memory: 1.5Gi
|
||
|
|
limits:
|
||
|
|
cpu: 1000m
|
||
|
|
memory: 2Gi
|
||
|
|
nvidia.com/gpu: "1"
|