Files
GenAIExamples/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml
lvliang-intel 3fb60608b3 Use official tei gaudi image and update tgi gaudi version (#810)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-23 17:52:56 +08:00

548 lines
14 KiB
YAML

---
# Source: codegen/charts/codegen-ui/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: codegen-codegen-ui-config
labels:
helm.sh/chart: codegen-ui-1.0.0
app.kubernetes.io/name: codegen-ui
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
data:
APP_BACKEND_SERVICE_ENDPOINT: "/v1/codegen"
APP_DATA_PREP_SERVICE_URL: "/v1/dataprep"
CHAT_BASE_URL: "/v1/codegen"
UPLOAD_FILE_BASE_URL: "/v1/dataprep"
GET_FILE: "/v1/dataprep/get_file"
DELETE_FILE: "/v1/dataprep/delete_file"
BASE_URL: "/v1/codegen"
DOC_BASE_URL: "/v1/codegen"
BASIC_URL: "/v1/codegen"
VITE_CODE_GEN_URL: "/v1/codegen"
VITE_DOC_SUM_URL: "/v1/codegen"
---
# Source: codegen/charts/llm-uservice/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: codegen-llm-uservice-config
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
data:
TGI_LLM_ENDPOINT: "http://codegen-tgi"
HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
HF_HOME: "/tmp/.cache/huggingface"
http_proxy: ""
https_proxy: ""
no_proxy: ""
LOGFLAG: ""
---
# Source: codegen/charts/tgi/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: codegen-tgi-config
labels:
helm.sh/chart: tgi-1.0.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "2.1.0"
app.kubernetes.io/managed-by: Helm
data:
MODEL_ID: "meta-llama/CodeLlama-7b-hf"
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"
---
# Source: codegen/templates/nginx-deployment.yaml
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://codegen-codegen-ui:5174;
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/codegen {
proxy_pass http://codegen:7778;
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: codegen-nginx-config
---
# Source: codegen/charts/codegen-ui/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: codegen-codegen-ui
labels:
helm.sh/chart: codegen-ui-1.0.0
app.kubernetes.io/name: codegen-ui
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 5174
targetPort: ui
protocol: TCP
name: ui
selector:
app.kubernetes.io/name: codegen-ui
app.kubernetes.io/instance: codegen
---
# Source: codegen/charts/llm-uservice/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: codegen-llm-uservice
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 9000
targetPort: 9000
protocol: TCP
name: llm-uservice
selector:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
---
# Source: codegen/charts/tgi/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: codegen-tgi
labels:
helm.sh/chart: tgi-1.0.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "2.1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 80
targetPort: 2080
protocol: TCP
name: tgi
selector:
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
---
# Source: codegen/templates/nginx-deployment.yaml
apiVersion: v1
kind: Service
metadata:
name: codegen-nginx
spec:
ports:
- port: 80
protocol: TCP
targetPort: 80
selector:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app: codegen-nginx
type: NodePort
---
# Source: codegen/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: codegen
labels:
helm.sh/chart: codegen-1.0.0
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 7778
targetPort: 7778
protocol: TCP
name: codegen
selector:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app: codegen
---
# Source: codegen/charts/codegen-ui/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: codegen-codegen-ui
labels:
helm.sh/chart: codegen-ui-1.0.0
app.kubernetes.io/name: codegen-ui
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: codegen-ui
app.kubernetes.io/instance: codegen
template:
metadata:
labels:
helm.sh/chart: codegen-ui-1.0.0
app.kubernetes.io/name: codegen-ui
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
securityContext:
{}
containers:
- name: codegen-ui
envFrom:
- configMapRef:
name: codegen-codegen-ui-config
securityContext:
{}
image: "opea/codegen-ui:latest"
imagePullPolicy: IfNotPresent
ports:
- name: ui
containerPort: 5173
protocol: TCP
resources:
{}
volumeMounts:
- mountPath: /tmp
name: tmp
volumes:
- name: tmp
emptyDir: {}
---
# Source: codegen/charts/llm-uservice/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: codegen-llm-uservice
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
template:
metadata:
labels:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
spec:
securityContext:
{}
containers:
- name: codegen
envFrom:
- configMapRef:
name: codegen-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: {}
---
# Source: codegen/charts/tgi/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: codegen-tgi
labels:
helm.sh/chart: tgi-1.0.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "2.1.0"
app.kubernetes.io/managed-by: Helm
spec:
# use explicit replica counts only of HorizontalPodAutoscaler is disabled
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
template:
metadata:
labels:
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
spec:
securityContext:
{}
containers:
- name: tgi
envFrom:
- configMapRef:
name: codegen-tgi-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/tgi-gaudi:2.0.5"
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:
limits:
habana.ai/gaudi: 1
memory: 64Gi
hugepages-2Mi: 500Mi
volumes:
- name: model-volume
emptyDir: {}
- name: tmp
emptyDir: {}
---
# Source: codegen/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: codegen
labels:
helm.sh/chart: codegen-1.0.0
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
app: codegen
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app: codegen
template:
metadata:
labels:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app: codegen
spec:
securityContext:
null
containers:
- name: codegen
env:
- name: LLM_SERVICE_HOST_IP
value: codegen-llm-uservice
#- name: MEGA_SERVICE_PORT
# value: 7778
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/codegen:latest"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /tmp
name: tmp
ports:
- name: codegen
containerPort: 7778
protocol: TCP
resources:
null
volumes:
- name: tmp
emptyDir: {}
---
# Source: codegen/templates/nginx-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: codegen-nginx
labels:
helm.sh/chart: codegen-1.0.0
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
app: codegen-nginx
spec:
selector:
matchLabels:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app: codegen-nginx
template:
metadata:
labels:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app: codegen-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: codegen-nginx-config
name: nginx-config-volume