[Translation] Support manifests and nginx (#812)
Signed-off-by: letonghan <letong.han@intel.com> Signed-off-by: root <root@a4bf019305c5.jf.intel.com> Co-authored-by: root <root@a4bf019305c5.jf.intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Letong Han
41
Translation/kubernetes/intel/README.md
Normal file
41
Translation/kubernetes/intel/README.md
Normal file
@@ -0,0 +1,41 @@
|
||||
# Deploy Translation in Kubernetes Cluster
|
||||
|
||||
> [NOTE]
|
||||
> The following values must be set before you can deploy:
|
||||
> HUGGINGFACEHUB_API_TOKEN
|
||||
>
|
||||
> You can also customize the "MODEL_ID" if needed.
|
||||
>
|
||||
> You need to make sure you have created the directory `/mnt/opea-models` to save the cached model on the node where the Translation workload is running. Otherwise, you need to modify the `translation.yaml` file to change the `model-volume` to a directory that exists on the node.
|
||||
|
||||
## Deploy On Xeon
|
||||
|
||||
```
|
||||
cd GenAIExamples/Translation/kubernetes/intel/cpu/xeon/manifests
|
||||
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
|
||||
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" translation.yaml
|
||||
kubectl apply -f translation.yaml
|
||||
```
|
||||
|
||||
## Deploy On Gaudi
|
||||
|
||||
```
|
||||
cd GenAIExamples/Translation/kubernetes/intel/hpu/gaudi/manifests
|
||||
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
|
||||
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" translation.yaml
|
||||
kubectl apply -f translation.yaml
|
||||
```
|
||||
|
||||
## Verify Services
|
||||
|
||||
To verify the installation, run the command `kubectl get pod` to make sure all pods are running.
|
||||
|
||||
Then run the command `kubectl port-forward svc/translation 8888:8888` to expose the Translation service for access.
|
||||
|
||||
Open another terminal and run the following command to verify the service if working:
|
||||
|
||||
```console
|
||||
curl http://localhost:8888/v1/translation \
|
||||
-H 'Content-Type: application/json' \
|
||||
-d '{"language_from": "Chinese","language_to": "English","source_language": "我爱机器翻译。"}'
|
||||
```
|
||||
495
Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml
Normal file
495
Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml
Normal file
@@ -0,0 +1,495 @@
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: translation-tgi-config
|
||||
labels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "2.1.0"
|
||||
data:
|
||||
LLM_MODEL_ID: "haoranxu/ALMA-13B"
|
||||
PORT: "2080"
|
||||
HF_TOKEN: "insert-your-huggingface-token-here"
|
||||
http_proxy: ""
|
||||
https_proxy: ""
|
||||
no_proxy: ""
|
||||
HABANA_LOGS: "/tmp/habana_logs"
|
||||
NUMBA_CACHE_DIR: "/tmp"
|
||||
HF_HOME: "/tmp/.cache/huggingface"
|
||||
CUDA_GRAPHS: "0"
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: translation-llm-uservice-config
|
||||
labels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
data:
|
||||
TGI_LLM_ENDPOINT: "http://translation-tgi"
|
||||
HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
|
||||
http_proxy: ""
|
||||
https_proxy: ""
|
||||
no_proxy: ""
|
||||
LOGFLAG: ""
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: translation-ui-config
|
||||
labels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
data:
|
||||
BASE_URL: "/v1/translation"
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
data:
|
||||
default.conf: |+
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
|
||||
server {
|
||||
listen 80;
|
||||
listen [::]:80;
|
||||
|
||||
location /home {
|
||||
alias /usr/share/nginx/html/index.html;
|
||||
}
|
||||
|
||||
location / {
|
||||
proxy_pass http://translation-ui:5173;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
}
|
||||
|
||||
location /v1/translation {
|
||||
proxy_pass http://translation:8888;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
}
|
||||
}
|
||||
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: translation-nginx-config
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation-ui
|
||||
labels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 5173
|
||||
targetPort: ui
|
||||
protocol: TCP
|
||||
name: ui
|
||||
selector:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation-llm-uservice
|
||||
labels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 9000
|
||||
targetPort: 9000
|
||||
protocol: TCP
|
||||
name: llm-uservice
|
||||
selector:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation-tgi
|
||||
labels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "2.1.0"
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 80
|
||||
targetPort: 2080
|
||||
protocol: TCP
|
||||
name: tgi
|
||||
selector:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation-nginx
|
||||
spec:
|
||||
ports:
|
||||
- port: 80
|
||||
protocol: TCP
|
||||
targetPort: 80
|
||||
selector:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation-nginx
|
||||
type: NodePort
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 8888
|
||||
targetPort: 8888
|
||||
protocol: TCP
|
||||
name: translation
|
||||
selector:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation-ui
|
||||
labels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
securityContext:
|
||||
{}
|
||||
containers:
|
||||
- name: translation-ui
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: translation-ui-config
|
||||
securityContext:
|
||||
{}
|
||||
image: "opea/translation-ui:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: ui
|
||||
containerPort: 80
|
||||
protocol: TCP
|
||||
resources:
|
||||
{}
|
||||
volumeMounts:
|
||||
- mountPath: /tmp
|
||||
name: tmp
|
||||
volumes:
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation-llm-uservice
|
||||
labels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
spec:
|
||||
securityContext:
|
||||
{}
|
||||
containers:
|
||||
- name: translation
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: translation-llm-uservice-config
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: false
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
image: "opea/llm-tgi:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: llm-uservice
|
||||
containerPort: 9000
|
||||
protocol: TCP
|
||||
volumeMounts:
|
||||
- mountPath: /tmp
|
||||
name: tmp
|
||||
livenessProbe:
|
||||
failureThreshold: 24
|
||||
httpGet:
|
||||
path: v1/health_check
|
||||
port: llm-uservice
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: v1/health_check
|
||||
port: llm-uservice
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
startupProbe:
|
||||
failureThreshold: 120
|
||||
httpGet:
|
||||
path: v1/health_check
|
||||
port: llm-uservice
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
resources:
|
||||
{}
|
||||
volumes:
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation-tgi
|
||||
labels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "2.1.0"
|
||||
spec:
|
||||
# use explicit replica counts only of HorizontalPodAutoscaler is disabled
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
spec:
|
||||
securityContext:
|
||||
{}
|
||||
containers:
|
||||
- name: tgi
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: translation-tgi-config
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
|
||||
imagePullPolicy: IfNotPresent
|
||||
volumeMounts:
|
||||
- mountPath: /data
|
||||
name: model-volume
|
||||
- mountPath: /tmp
|
||||
name: tmp
|
||||
ports:
|
||||
- name: http
|
||||
containerPort: 2080
|
||||
protocol: TCP
|
||||
livenessProbe:
|
||||
failureThreshold: 24
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
tcpSocket:
|
||||
port: http
|
||||
readinessProbe:
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
tcpSocket:
|
||||
port: http
|
||||
startupProbe:
|
||||
failureThreshold: 120
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
tcpSocket:
|
||||
port: http
|
||||
resources:
|
||||
{}
|
||||
volumes:
|
||||
- name: model-volume
|
||||
emptyDir: {}
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
app: translation
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation
|
||||
spec:
|
||||
securityContext:
|
||||
null
|
||||
containers:
|
||||
- name: translation
|
||||
env:
|
||||
- name: LLM_SERVICE_HOST_IP
|
||||
value: translation-llm-uservice
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
image: "opea/translation:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
volumeMounts:
|
||||
- mountPath: /tmp
|
||||
name: tmp
|
||||
ports:
|
||||
- name: translation
|
||||
containerPort: 8888
|
||||
protocol: TCP
|
||||
resources:
|
||||
null
|
||||
volumes:
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation-nginx
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
app: translation-nginx
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation-nginx
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation-nginx
|
||||
spec:
|
||||
containers:
|
||||
- image: nginx:1.27.1
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: nginx
|
||||
volumeMounts:
|
||||
- mountPath: /etc/nginx/conf.d
|
||||
name: nginx-config-volume
|
||||
securityContext: {}
|
||||
volumes:
|
||||
- configMap:
|
||||
defaultMode: 420
|
||||
name: translation-nginx-config
|
||||
name: nginx-config-volume
|
||||
497
Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml
Normal file
497
Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml
Normal file
@@ -0,0 +1,497 @@
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: translation-tgi-config
|
||||
labels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "2.1.0"
|
||||
data:
|
||||
LLM_MODEL_ID: "haoranxu/ALMA-13B"
|
||||
PORT: "2080"
|
||||
HF_TOKEN: "insert-your-huggingface-token-here"
|
||||
http_proxy: ""
|
||||
https_proxy: ""
|
||||
no_proxy: ""
|
||||
HABANA_LOGS: "/tmp/habana_logs"
|
||||
NUMBA_CACHE_DIR: "/tmp"
|
||||
HF_HOME: "/tmp/.cache/huggingface"
|
||||
MAX_INPUT_LENGTH: "1024"
|
||||
MAX_TOTAL_TOKENS: "2048"
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: translation-llm-uservice-config
|
||||
labels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
data:
|
||||
TGI_LLM_ENDPOINT: "http://translation-tgi"
|
||||
HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
|
||||
http_proxy: ""
|
||||
https_proxy: ""
|
||||
no_proxy: ""
|
||||
LOGFLAG: ""
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: translation-ui-config
|
||||
labels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
data:
|
||||
BASE_URL: "/v1/translation"
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
data:
|
||||
default.conf: |+
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
|
||||
server {
|
||||
listen 80;
|
||||
listen [::]:80;
|
||||
|
||||
location /home {
|
||||
alias /usr/share/nginx/html/index.html;
|
||||
}
|
||||
|
||||
location / {
|
||||
proxy_pass http://translation-ui:5173;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
}
|
||||
|
||||
location /v1/translation {
|
||||
proxy_pass http://translation;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
}
|
||||
}
|
||||
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: translation-nginx-config
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation-ui
|
||||
labels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 5173
|
||||
targetPort: ui
|
||||
protocol: TCP
|
||||
name: ui
|
||||
selector:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation-llm-uservice
|
||||
labels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 9000
|
||||
targetPort: 9000
|
||||
protocol: TCP
|
||||
name: llm-uservice
|
||||
selector:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation-tgi
|
||||
labels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "2.1.0"
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 80
|
||||
targetPort: 2080
|
||||
protocol: TCP
|
||||
name: tgi
|
||||
selector:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation-nginx
|
||||
spec:
|
||||
ports:
|
||||
- port: 80
|
||||
protocol: TCP
|
||||
targetPort: 80
|
||||
selector:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation-nginx
|
||||
type: NodePort
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: translation
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 8888
|
||||
targetPort: 8888
|
||||
protocol: TCP
|
||||
name: translation
|
||||
selector:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation-ui
|
||||
labels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: translation-ui
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
securityContext:
|
||||
{}
|
||||
containers:
|
||||
- name: translation-ui
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: translation-ui-config
|
||||
securityContext:
|
||||
{}
|
||||
image: "opea/translation-ui:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: ui
|
||||
containerPort: 80
|
||||
protocol: TCP
|
||||
resources:
|
||||
{}
|
||||
volumeMounts:
|
||||
- mountPath: /tmp
|
||||
name: tmp
|
||||
volumes:
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation-llm-uservice
|
||||
labels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: translation
|
||||
spec:
|
||||
securityContext:
|
||||
{}
|
||||
containers:
|
||||
- name: translation
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: translation-llm-uservice-config
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: false
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
image: "opea/llm-tgi:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: llm-uservice
|
||||
containerPort: 9000
|
||||
protocol: TCP
|
||||
volumeMounts:
|
||||
- mountPath: /tmp
|
||||
name: tmp
|
||||
livenessProbe:
|
||||
failureThreshold: 24
|
||||
httpGet:
|
||||
path: v1/health_check
|
||||
port: llm-uservice
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: v1/health_check
|
||||
port: llm-uservice
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
startupProbe:
|
||||
failureThreshold: 120
|
||||
httpGet:
|
||||
path: v1/health_check
|
||||
port: llm-uservice
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
resources:
|
||||
{}
|
||||
volumes:
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation-tgi
|
||||
labels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "2.1.0"
|
||||
spec:
|
||||
# use explicit replica counts only of HorizontalPodAutoscaler is disabled
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: translation
|
||||
spec:
|
||||
securityContext:
|
||||
{}
|
||||
containers:
|
||||
- name: tgi
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: translation-tgi-config
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
image: "ghcr.io/huggingface/tgi-gaudi:2.0.1"
|
||||
imagePullPolicy: IfNotPresent
|
||||
volumeMounts:
|
||||
- mountPath: /data
|
||||
name: model-volume
|
||||
- mountPath: /tmp
|
||||
name: tmp
|
||||
ports:
|
||||
- name: http
|
||||
containerPort: 2080
|
||||
protocol: TCP
|
||||
livenessProbe:
|
||||
failureThreshold: 24
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
tcpSocket:
|
||||
port: http
|
||||
readinessProbe:
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
tcpSocket:
|
||||
port: http
|
||||
startupProbe:
|
||||
failureThreshold: 120
|
||||
initialDelaySeconds: 20
|
||||
periodSeconds: 5
|
||||
tcpSocket:
|
||||
port: http
|
||||
resources:
|
||||
limits:
|
||||
habana.ai/gaudi: 1
|
||||
volumes:
|
||||
- name: model-volume
|
||||
emptyDir: {}
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
app: translation
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation
|
||||
spec:
|
||||
securityContext:
|
||||
null
|
||||
containers:
|
||||
- name: translation
|
||||
env:
|
||||
- name: LLM_SERVICE_HOST_IP
|
||||
value: translation-llm-uservice
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
image: "opea/translation:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
volumeMounts:
|
||||
- mountPath: /tmp
|
||||
name: tmp
|
||||
ports:
|
||||
- name: translation
|
||||
containerPort: 8888
|
||||
protocol: TCP
|
||||
resources:
|
||||
null
|
||||
volumes:
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
---
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: translation-nginx
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app.kubernetes.io/version: "v1.0"
|
||||
app: translation-nginx
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation-nginx
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: translation
|
||||
app.kubernetes.io/instance: translation
|
||||
app: translation-nginx
|
||||
spec:
|
||||
containers:
|
||||
- image: nginx:1.27.1
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: nginx
|
||||
volumeMounts:
|
||||
- mountPath: /etc/nginx/conf.d
|
||||
name: nginx-config-volume
|
||||
securityContext: {}
|
||||
volumes:
|
||||
- configMap:
|
||||
defaultMode: 420
|
||||
name: translation-nginx-config
|
||||
name: nginx-config-volume
|
||||
Reference in New Issue
Block a user