Files
GenAIExamples/ChatQnA/benchmark/two_gaudi/llm-microservice_run.yaml
Zhenzhong1 08f57fa54a update manifests for v0.9 (#623)
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-08-19 15:55:04 +08:00

60 lines
1.2 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: llm-deploy
namespace: default
spec:
replicas: 1
selector:
matchLabels:
app: llm-deploy
template:
metadata:
annotations:
sidecar.istio.io/rewriteAppHTTPProbers: 'true'
labels:
app: llm-deploy
spec:
nodeSelector:
node-type: chatqna-opea
topologySpreadConstraints:
- maxSkew: 1
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: ScheduleAnyway
labelSelector:
matchLabels:
app: llm-deploy
hostIPC: true
containers:
- envFrom:
- configMapRef:
name: qna-config
image: opea/llm-tgi:latest
imagePullPolicy: IfNotPresent
name: llm-deploy
args: null
ports:
- containerPort: 9000
resources:
limits:
cpu: 4
requests:
cpu: 4
serviceAccountName: default
---
kind: Service
apiVersion: v1
metadata:
name: llm-svc
spec:
type: ClusterIP
selector:
app: llm-deploy
ports:
- name: service
port: 9000
targetPort: 9000