Refactor folder to support different vendors (#743)
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com> Signed-off-by: chensuyue <suyue.chen@intel.com>
This commit is contained in:
XinyaoWa
48
CodeGen/kubernetes/intel/README.md
Normal file
48
CodeGen/kubernetes/intel/README.md
Normal file
@@ -0,0 +1,48 @@
|
||||
# Deploy CodeGen 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 CodeGen workload is running. Otherwise, you need to modify the `codegen.yaml` file to change the `model-volume` to a directory that exists on the node.
|
||||
> Alternatively, you can change the `codegen.yaml` to use a different type of volume, such as a persistent volume claim.
|
||||
|
||||
## Deploy On Xeon
|
||||
|
||||
```
|
||||
cd GenAIExamples/CodeGen/kubernetes/manifests/xeon
|
||||
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
|
||||
export MODEL_ID="meta-llama/CodeLlama-7b-hf"
|
||||
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml
|
||||
sed -i "s/meta-llama\/CodeLlama-7b-hf/${MODEL_ID}/g" codegen.yaml
|
||||
kubectl apply -f codegen.yaml
|
||||
```
|
||||
|
||||
## Deploy On Gaudi
|
||||
|
||||
```
|
||||
cd GenAIExamples/CodeGen/kubernetes/manifests/gaudi
|
||||
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
|
||||
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml
|
||||
kubectl apply -f codegen.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/codegen 7778:7778` to expose the CodeGen service for access.
|
||||
|
||||
Open another terminal and run the following command to verify the service if working:
|
||||
|
||||
> Note that it may take a couple of minutes for the service to be ready. If the `curl` command below fails, you
|
||||
> can check the logs of the codegen-tgi pod to see its status or check for errors.
|
||||
|
||||
```
|
||||
kubectl get pods
|
||||
curl http://localhost:7778/v1/codegen -H "Content-Type: application/json" -d '{
|
||||
"messages": "Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception."
|
||||
}'
|
||||
```
|
||||
40
CodeGen/kubernetes/intel/README_gmc.md
Normal file
40
CodeGen/kubernetes/intel/README_gmc.md
Normal file
@@ -0,0 +1,40 @@
|
||||
# Deploy CodeGen in a Kubernetes Cluster
|
||||
|
||||
This document outlines the deployment process for a Code Generation (CodeGen) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
|
||||
|
||||
Install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
|
||||
|
||||
If you have only Intel Xeon machines you could use the codegen_xeon.yaml file or if you have a Gaudi cluster you could use codegen_gaudi.yaml
|
||||
In the below example we illustrate on Xeon.
|
||||
|
||||
## Deploy the RAG application
|
||||
|
||||
1. Create the desired namespace if it does not already exist and deploy the application
|
||||
```bash
|
||||
export APP_NAMESPACE=CT
|
||||
kubectl create ns $APP_NAMESPACE
|
||||
sed -i "s|namespace: codegen|namespace: $APP_NAMESPACE|g" ./codegen_xeon.yaml
|
||||
kubectl apply -f ./codegen_xeon.yaml
|
||||
```
|
||||
|
||||
2. Check if the application is up and ready
|
||||
```bash
|
||||
kubectl get pods -n $APP_NAMESPACE
|
||||
```
|
||||
|
||||
3. Deploy a client pod for testing
|
||||
```bash
|
||||
kubectl create deployment client-test -n $APP_NAMESPACE --image=python:3.8.13 -- sleep infinity
|
||||
```
|
||||
|
||||
4. Check that client pod is ready
|
||||
```bash
|
||||
kubectl get pods -n $APP_NAMESPACE
|
||||
```
|
||||
|
||||
5. Send request to application
|
||||
```bash
|
||||
export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
|
||||
export accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='codegen')].status.accessUrl}")
|
||||
kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl -s --no-buffer $accessUrl -X POST -d '{"query": "def print_hello_world():"}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_codegen.log
|
||||
```
|
||||
34
CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml
Normal file
34
CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml
Normal file
@@ -0,0 +1,34 @@
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: gmc.opea.io/v1alpha3
|
||||
kind: GMConnector
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: gmconnector
|
||||
app.kubernetes.io/managed-by: kustomize
|
||||
gmc/platform: xeon
|
||||
name: codegen
|
||||
namespace: codegen
|
||||
spec:
|
||||
routerConfig:
|
||||
name: router
|
||||
serviceName: router-service
|
||||
nodes:
|
||||
root:
|
||||
routerType: Sequence
|
||||
steps:
|
||||
- name: Llm
|
||||
data: $response
|
||||
internalService:
|
||||
serviceName: llm-service
|
||||
config:
|
||||
endpoint: /v1/chat/completions
|
||||
TGI_LLM_ENDPOINT: tgi-service
|
||||
- name: Tgi
|
||||
internalService:
|
||||
serviceName: tgi-service
|
||||
config:
|
||||
MODEL_ID: meta-llama/CodeLlama-7b-hf
|
||||
endpoint: /generate
|
||||
isDownstreamService: true
|
||||
@@ -0,0 +1,38 @@
|
||||
# Deploy CodeGen with ReactUI
|
||||
|
||||
The README provides a step-by-step guide on how to deploy CodeGen with ReactUI, a popular React-based user interface library in Kubernetes cluster.
|
||||
|
||||
You can use react-codegen.yaml to deploy CodeGen with reactUI.
|
||||
```
|
||||
kubectl apply -f react-codegen.yaml
|
||||
```
|
||||
|
||||
## Prerequisites for Deploying CodeGen with ReactUI
|
||||
Before deploying the react-codegen.yaml file, ensure that you have the following prerequisites in place:
|
||||
|
||||
1. Kubernetes installation: Make sure that you have Kubernetes installed.
|
||||
2. Configuration Values: Set the following values in react-codegen.yaml before proceeding with the deployment:
|
||||
|
||||
a. HUGGINGFACEHUB_API_TOKEN (Your HuggingFace token to download your desired model from HuggingFace):
|
||||
```
|
||||
# You may set the HUGGINGFACEHUB_API_TOKEN via method:
|
||||
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
|
||||
cd GenAIExamples/CodeGen/kubernetes/manifests/xeon/ui/
|
||||
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" react-codegen.yaml
|
||||
```
|
||||
b. Set the proxies based on your network configuration
|
||||
```
|
||||
# Look for http_proxy, https_proxy, no_proxy key and fill up the value with your proxy configuration.
|
||||
```
|
||||
3. MODEL_ID and model-volume (OPTIONAL): You may as well customize the "MODEL_ID" to use different model and model-volume for the volume to be mounted.
|
||||
4. After completing these, you can proceed with the deployment of the react-codegen.yaml file.
|
||||
|
||||
## Verify Services
|
||||
Make sure all the pods are running, you should see total of 4 pods running:
|
||||
|
||||
- codegen
|
||||
- codegen-llm-uservice
|
||||
- codegen-react-ui
|
||||
- codegen-tgi
|
||||
|
||||
You may open up the UI by using the codegen-react-ui endpoint in the browser.
|
||||
543
CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml
Normal file
543
CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml
Normal file
@@ -0,0 +1,543 @@
|
||||
---
|
||||
# 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"
|
||||
CUDA_GRAPHS: "0"
|
||||
---
|
||||
# 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/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: {}
|
||||
---
|
||||
# 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
|
||||
282
CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml
Normal file
282
CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml
Normal file
@@ -0,0 +1,282 @@
|
||||
---
|
||||
# Source: codegen/charts/llm-uservice/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-0.1.0
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: codegen
|
||||
app.kubernetes.io/version: "1.4"
|
||||
app.kubernetes.io/managed-by: Helm
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 80
|
||||
targetPort: 80
|
||||
protocol: TCP
|
||||
name: tgi
|
||||
selector:
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: codegen
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: codegen-llm-uservice
|
||||
labels:
|
||||
helm.sh/chart: llm-uservice-0.1.0
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: codegen
|
||||
app.kubernetes.io/version: "1.0.0"
|
||||
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
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: codegen
|
||||
labels:
|
||||
helm.sh/chart: codegen-0.1.0
|
||||
app.kubernetes.io/name: codegen
|
||||
app.kubernetes.io/instance: codegen
|
||||
app.kubernetes.io/version: "1.0.0"
|
||||
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
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: codegen-react-ui
|
||||
labels:
|
||||
helm.sh/chart: codegen-react-ui-0.1.0
|
||||
app.kubernetes.io/name: react-ui
|
||||
app.kubernetes.io/instance: codegen
|
||||
app.kubernetes.io/version: "1.0.0"
|
||||
app.kubernetes.io/managed-by: Helm
|
||||
spec:
|
||||
type: ClusterIP
|
||||
ports:
|
||||
- port: 80
|
||||
targetPort: 80
|
||||
protocol: TCP
|
||||
name: react-ui
|
||||
selector:
|
||||
app.kubernetes.io/name: react-ui
|
||||
app.kubernetes.io/instance: codegen
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: codegen-tgi
|
||||
labels:
|
||||
helm.sh/chart: tgi-0.1.0
|
||||
app.kubernetes.io/name: tgi
|
||||
app.kubernetes.io/instance: codegen
|
||||
app.kubernetes.io/version: "1.4"
|
||||
app.kubernetes.io/managed-by: Helm
|
||||
spec:
|
||||
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
|
||||
env:
|
||||
- name: MODEL_ID
|
||||
value: ise-uiuc/Magicoder-S-DS-6.7B
|
||||
- name: PORT
|
||||
value: "80"
|
||||
- name: CUDA_GRAPHS
|
||||
value: "0"
|
||||
- name: http_proxy
|
||||
value:
|
||||
- name: https_proxy
|
||||
value:
|
||||
- name: no_proxy
|
||||
value:
|
||||
securityContext: {}
|
||||
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
|
||||
imagePullPolicy: IfNotPresent
|
||||
volumeMounts:
|
||||
- mountPath: /data
|
||||
name: model-volume
|
||||
ports:
|
||||
- name: http
|
||||
containerPort: 80
|
||||
protocol: TCP
|
||||
resources: {}
|
||||
volumes:
|
||||
- name: model-volume
|
||||
hostPath:
|
||||
path: /mnt
|
||||
type: Directory
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: codegen-llm-uservice
|
||||
labels:
|
||||
helm.sh/chart: llm-uservice-0.1.0
|
||||
app.kubernetes.io/name: llm-uservice
|
||||
app.kubernetes.io/instance: codegen
|
||||
app.kubernetes.io/version: "1.0.0"
|
||||
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
|
||||
env:
|
||||
- name: TGI_LLM_ENDPOINT
|
||||
value: "http://codegen-tgi:80"
|
||||
- name: HUGGINGFACEHUB_API_TOKEN
|
||||
value: "insert-your-huggingface-token-here"
|
||||
- name: http_proxy
|
||||
value:
|
||||
- name: https_proxy
|
||||
value:
|
||||
- name: no_proxy
|
||||
value:
|
||||
securityContext: {}
|
||||
image: "opea/llm-tgi:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: llm-uservice
|
||||
containerPort: 9000
|
||||
protocol: TCP
|
||||
startupProbe:
|
||||
exec:
|
||||
command:
|
||||
- curl
|
||||
- http://codegen-tgi:80
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
failureThreshold: 120
|
||||
resources: {}
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: codegen
|
||||
labels:
|
||||
helm.sh/chart: codegen-0.1.0
|
||||
app.kubernetes.io/name: codegen
|
||||
app.kubernetes.io/instance: codegen
|
||||
app.kubernetes.io/version: "1.0.0"
|
||||
app.kubernetes.io/managed-by: Helm
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: codegen
|
||||
app.kubernetes.io/instance: codegen
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: codegen
|
||||
app.kubernetes.io/instance: codegen
|
||||
spec:
|
||||
securityContext: null
|
||||
containers:
|
||||
- name: codegen
|
||||
env:
|
||||
- name: LLM_SERVICE_HOST_IP
|
||||
value: codegen-llm-uservice
|
||||
- name: http_proxy
|
||||
value:
|
||||
- name: https_proxy
|
||||
value:
|
||||
- name: no_proxy
|
||||
value:
|
||||
securityContext: null
|
||||
image: "opea/codegen:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: codegen
|
||||
containerPort: 7778
|
||||
protocol: TCP
|
||||
resources: null
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: codegen-react-ui
|
||||
labels:
|
||||
helm.sh/chart: codegen-react-ui-0.1.0
|
||||
app.kubernetes.io/name: react-ui
|
||||
app.kubernetes.io/instance: codegen
|
||||
app.kubernetes.io/version: "1.0.0"
|
||||
app.kubernetes.io/managed-by: Helm
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: react-ui
|
||||
app.kubernetes.io/instance: codegen
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: react-ui
|
||||
app.kubernetes.io/instance: codegen
|
||||
spec:
|
||||
securityContext: null
|
||||
containers:
|
||||
- name: codegen-react-ui
|
||||
env:
|
||||
- name: BASIC_URL
|
||||
value: "http://codegen:7778/v1/codegen"
|
||||
- name: http_proxy
|
||||
value:
|
||||
- name: https_proxy
|
||||
value:
|
||||
- name: no_proxy
|
||||
value:
|
||||
securityContext: null
|
||||
image: "opea/codegen-react-ui:latest"
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: react-ui
|
||||
containerPort: 80
|
||||
protocol: TCP
|
||||
resources: null
|
||||
34
CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml
Normal file
34
CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml
Normal file
@@ -0,0 +1,34 @@
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: gmc.opea.io/v1alpha3
|
||||
kind: GMConnector
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: gmconnector
|
||||
app.kubernetes.io/managed-by: kustomize
|
||||
gmc/platform: gaudi
|
||||
name: codegen
|
||||
namespace: codegen
|
||||
spec:
|
||||
routerConfig:
|
||||
name: router
|
||||
serviceName: router-service
|
||||
nodes:
|
||||
root:
|
||||
routerType: Sequence
|
||||
steps:
|
||||
- name: Llm
|
||||
data: $response
|
||||
internalService:
|
||||
serviceName: llm-service
|
||||
config:
|
||||
endpoint: /v1/chat/completions
|
||||
TGI_LLM_ENDPOINT: tgi-gaudi-svc
|
||||
- name: TgiGaudi
|
||||
internalService:
|
||||
serviceName: tgi-gaudi-svc
|
||||
config:
|
||||
MODEL_ID: meta-llama/CodeLlama-7b-hf
|
||||
endpoint: /generate
|
||||
isDownstreamService: true
|
||||
547
CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml
Normal file
547
CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml
Normal file
@@ -0,0 +1,547 @@
|
||||
---
|
||||
# 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:2.0.1"
|
||||
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: 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
|
||||
Reference in New Issue
Block a user