Nik Afiq
f2261a2676
Some checks failed
validate / lint (push) Failing after 1s
Deploys the Go gRPC gateway and Python/libtorch inference sidecar as one pod on nik-gpu (nodeSelector/toleration/runtimeClassName: nvidia, sidecar requesting nvidia.com/gpu: 1), matching the existing GPU device plugin. Model checkpoint/config are bind-mounted from /data/tts-gateway, added to gpu-node's Ansible data_dirs for consistency with the other hosts. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
137 lines
3.7 KiB
YAML
137 lines
3.7 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: tts-gateway
|
|
namespace: home-services
|
|
labels:
|
|
app: tts-gateway
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: tts-gateway
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: tts-gateway
|
|
spec:
|
|
runtimeClassName: nvidia
|
|
nodeSelector:
|
|
nik4nao.com/gpu: "true"
|
|
tolerations:
|
|
- key: spot
|
|
operator: Equal
|
|
value: "true"
|
|
effect: NoSchedule
|
|
imagePullSecrets:
|
|
- name: gitea-registry-secret
|
|
containers:
|
|
- name: tts-gateway
|
|
image: gitea.nik4nao.com/nik/tts-gateway:latest
|
|
ports:
|
|
- containerPort: 50053
|
|
name: grpc
|
|
env:
|
|
- name: GRPC_PORT
|
|
value: "50053"
|
|
- name: INFERENCE_SIDECAR_ADDR
|
|
value: "localhost:50054"
|
|
- name: OTEL_ENDPOINT
|
|
value: "otel-collector-opentelemetry-collector.monitoring.svc.cluster.local:4317"
|
|
- name: LOG_LEVEL
|
|
value: "info"
|
|
- name: LOG_FORMAT
|
|
value: "json"
|
|
- name: TLS_DIR
|
|
value: /tls
|
|
readinessProbe:
|
|
tcpSocket:
|
|
port: 50053
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 10
|
|
livenessProbe:
|
|
tcpSocket:
|
|
port: 50053
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 30
|
|
resources:
|
|
requests:
|
|
cpu: 50m
|
|
memory: 64Mi
|
|
limits:
|
|
cpu: 200m
|
|
memory: 128Mi
|
|
volumeMounts:
|
|
- name: tls
|
|
mountPath: /tls
|
|
readOnly: true
|
|
# Needs an Nvidia GPU for net_g.infer() - only meaningfully runs on
|
|
# nik-gpu. Shares the pod network with tts-gateway so the Go side can
|
|
# reach it over localhost, mirroring the --network host setup used
|
|
# for local docker testing (see tts-gateway/README.md).
|
|
- name: tts-sidecar
|
|
image: gitea.nik4nao.com/nik/tts-sidecar:latest
|
|
ports:
|
|
- containerPort: 50054
|
|
name: http
|
|
env:
|
|
- name: PORT
|
|
value: "50054"
|
|
- name: CONFIG_PATH
|
|
value: /models/uma.json
|
|
- name: CHECKPOINT_PATH
|
|
value: /models/G_790000.pth
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /health
|
|
port: 50054
|
|
initialDelaySeconds: 15
|
|
periodSeconds: 10
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /health
|
|
port: 50054
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 30
|
|
resources:
|
|
requests:
|
|
cpu: 500m
|
|
memory: 3Gi
|
|
nvidia.com/gpu: 1
|
|
limits:
|
|
cpu: "2"
|
|
memory: 6Gi
|
|
nvidia.com/gpu: 1
|
|
volumeMounts:
|
|
- name: models
|
|
mountPath: /models
|
|
readOnly: true
|
|
volumes:
|
|
- name: tls
|
|
secret:
|
|
secretName: tts-gateway-tls
|
|
# Checkpoint/config aren't baked into the sidecar image (still an
|
|
# open decision per tts-gateway/README.md) - bind-mounted from
|
|
# /data/tts-gateway on nik-gpu instead. Populate with G_790000.pth
|
|
# and uma.json before this Deployment will go Ready.
|
|
- name: models
|
|
hostPath:
|
|
path: /data/tts-gateway
|
|
type: Directory
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: tts-gateway
|
|
namespace: home-services
|
|
labels:
|
|
app: tts-gateway
|
|
spec:
|
|
selector:
|
|
app: tts-gateway
|
|
ports:
|
|
- name: grpc
|
|
port: 50053
|
|
targetPort: 50053
|
|
type: ClusterIP
|