From 5638075d6574895702de7eff2014b95dc41864bf Mon Sep 17 00:00:00 2001 From: dolpher Date: Wed, 8 Jan 2025 13:20:32 +0800 Subject: [PATCH] Add helm deployment instructions for codegen (#1351) Signed-off-by: Dolpher Du --- CodeGen/README.md | 8 +- .../{intel/README_gmc.md => gmc/README.md} | 0 .../hpu/gaudi => }/gmc/codegen_gaudi.yaml | 0 .../cpu/xeon => }/gmc/codegen_xeon.yaml | 0 CodeGen/kubernetes/helm/README.md | 18 + CodeGen/kubernetes/helm/cpu-values.yaml | 9 + CodeGen/kubernetes/helm/gaudi-values.yaml | 28 + CodeGen/kubernetes/intel/README.md | 48 -- .../cpu/xeon/manifest/README_react_ui.md | 38 -- .../intel/cpu/xeon/manifest/codegen.yaml | 543 ----------------- .../cpu/xeon/manifest/codegen_react_ui.yaml | 282 --------- .../intel/hpu/gaudi/manifest/codegen.yaml | 547 ------------------ CodeGen/tests/test_gmc_on_gaudi.sh | 4 +- CodeGen/tests/test_gmc_on_xeon.sh | 4 +- README.md | 26 +- 15 files changed, 73 insertions(+), 1482 deletions(-) rename CodeGen/kubernetes/{intel/README_gmc.md => gmc/README.md} (100%) rename CodeGen/kubernetes/{intel/hpu/gaudi => }/gmc/codegen_gaudi.yaml (100%) rename CodeGen/kubernetes/{intel/cpu/xeon => }/gmc/codegen_xeon.yaml (100%) create mode 100644 CodeGen/kubernetes/helm/README.md create mode 100644 CodeGen/kubernetes/helm/cpu-values.yaml create mode 100644 CodeGen/kubernetes/helm/gaudi-values.yaml delete mode 100644 CodeGen/kubernetes/intel/README.md delete mode 100644 CodeGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md delete mode 100644 CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml delete mode 100644 CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml delete mode 100644 CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml diff --git a/CodeGen/README.md b/CodeGen/README.md index 013c31d37..c79f70738 100644 --- a/CodeGen/README.md +++ b/CodeGen/README.md @@ -145,15 +145,9 @@ docker compose up -d Refer to the [Xeon Guide](./docker_compose/intel/cpu/xeon/README.md) for more instructions on building docker images from source. -### Deploy CodeGen using Kubernetes - -Refer to the [Kubernetes Guide](./kubernetes/intel/README.md) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi. - ### Deploy CodeGen into Kubernetes using Helm Chart -Install Helm (version >= 3.15) first. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information. - -Refer to the [CodeGen helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codegen/README.md) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi. +Refer to the [CodeGen helm chart](./kubernetes/helm/README.md) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi. ## Consume CodeGen Service diff --git a/CodeGen/kubernetes/intel/README_gmc.md b/CodeGen/kubernetes/gmc/README.md similarity index 100% rename from CodeGen/kubernetes/intel/README_gmc.md rename to CodeGen/kubernetes/gmc/README.md diff --git a/CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml b/CodeGen/kubernetes/gmc/codegen_gaudi.yaml similarity index 100% rename from CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml rename to CodeGen/kubernetes/gmc/codegen_gaudi.yaml diff --git a/CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml b/CodeGen/kubernetes/gmc/codegen_xeon.yaml similarity index 100% rename from CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml rename to CodeGen/kubernetes/gmc/codegen_xeon.yaml diff --git a/CodeGen/kubernetes/helm/README.md b/CodeGen/kubernetes/helm/README.md new file mode 100644 index 000000000..45b5a363d --- /dev/null +++ b/CodeGen/kubernetes/helm/README.md @@ -0,0 +1,18 @@ +# Deploy CodeGen on kubernetes cluster + +- You should have Helm (version >= 3.15) installed. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information. +- For more deploy options, refer to [helm charts README](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts#readme). + +## Deploy on Xeon + +``` +export HFTOKEN="insert-your-huggingface-token-here" +helm install codegen oci://ghcr.io/opea-project/charts/codegen --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} -f cpu-values.yaml +``` + +## Deploy on Gaudi + +``` +export HFTOKEN="insert-your-huggingface-token-here" +helm install codegen oci://ghcr.io/opea-project/charts/codegen --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} -f gaudi-values.yaml +``` diff --git a/CodeGen/kubernetes/helm/cpu-values.yaml b/CodeGen/kubernetes/helm/cpu-values.yaml new file mode 100644 index 000000000..cfe41514b --- /dev/null +++ b/CodeGen/kubernetes/helm/cpu-values.yaml @@ -0,0 +1,9 @@ +# Copyright (C) 2024 Intel Corporation +# SPDX-License-Identifier: Apache-2.0 + +image: + repository: opea/codegen + tag: "latest" + +tgi: + LLM_MODEL_ID: Qwen/Qwen2.5-Coder-7B-Instruct diff --git a/CodeGen/kubernetes/helm/gaudi-values.yaml b/CodeGen/kubernetes/helm/gaudi-values.yaml new file mode 100644 index 000000000..e26bb4a5e --- /dev/null +++ b/CodeGen/kubernetes/helm/gaudi-values.yaml @@ -0,0 +1,28 @@ +# Copyright (C) 2024 Intel Corporation +# SPDX-License-Identifier: Apache-2.0 + +tgi: + accelDevice: "gaudi" + LLM_MODEL_ID: Qwen/Qwen2.5-Coder-7B-Instruct + image: + repository: ghcr.io/huggingface/tgi-gaudi + tag: "2.0.6" + resources: + limits: + habana.ai/gaudi: 1 + MAX_INPUT_LENGTH: "1024" + MAX_TOTAL_TOKENS: "2048" + CUDA_GRAPHS: "" + livenessProbe: + initialDelaySeconds: 5 + periodSeconds: 5 + timeoutSeconds: 1 + readinessProbe: + initialDelaySeconds: 5 + periodSeconds: 5 + timeoutSeconds: 1 + startupProbe: + initialDelaySeconds: 5 + periodSeconds: 5 + timeoutSeconds: 1 + failureThreshold: 120 diff --git a/CodeGen/kubernetes/intel/README.md b/CodeGen/kubernetes/intel/README.md deleted file mode 100644 index 0c47956a8..000000000 --- a/CodeGen/kubernetes/intel/README.md +++ /dev/null @@ -1,48 +0,0 @@ -# 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/intel/cpu/xeon/manifest -export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" -export MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct" -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/intel/hpu/gaudi/manifest -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." - }' -``` diff --git a/CodeGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md b/CodeGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md deleted file mode 100644 index c9911ee7d..000000000 --- a/CodeGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md +++ /dev/null @@ -1,38 +0,0 @@ -# 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/intel/cpu/xeon/manifest/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. diff --git a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml deleted file mode 100644 index 30fb919f0..000000000 --- a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml +++ /dev/null @@ -1,543 +0,0 @@ ---- -# 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: "Qwen/Qwen2.5-Coder-7B-Instruct" - 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-textgen: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:2.4.0-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 diff --git a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml deleted file mode 100644 index 1ebd1d4a4..000000000 --- a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml +++ /dev/null @@ -1,282 +0,0 @@ ---- -# 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:2.4.0-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-textgen: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 diff --git a/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml b/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml deleted file mode 100644 index 1273b943a..000000000 --- a/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml +++ /dev/null @@ -1,547 +0,0 @@ ---- -# 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: "Qwen/Qwen2.5-Coder-7B-Instruct" - 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-textgen: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:2.0.6" - 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 diff --git a/CodeGen/tests/test_gmc_on_gaudi.sh b/CodeGen/tests/test_gmc_on_gaudi.sh index 805237208..3804c2d4f 100755 --- a/CodeGen/tests/test_gmc_on_gaudi.sh +++ b/CodeGen/tests/test_gmc_on_gaudi.sh @@ -112,12 +112,12 @@ fi case "$1" in install_CodeGen) - pushd CodeGen/kubernetes/intel/hpu/gaudi/gmc + pushd CodeGen/kubernetes/gmc install_codegen popd ;; validate_CodeGen) - pushd CodeGen/kubernetes/intel/hpu/gaudi/gmc + pushd CodeGen/kubernetes/gmc validate_codegen popd ;; diff --git a/CodeGen/tests/test_gmc_on_xeon.sh b/CodeGen/tests/test_gmc_on_xeon.sh index 5f3ff0eae..97c14d793 100755 --- a/CodeGen/tests/test_gmc_on_xeon.sh +++ b/CodeGen/tests/test_gmc_on_xeon.sh @@ -112,12 +112,12 @@ fi case "$1" in install_CodeGen) - pushd CodeGen/kubernetes/intel/cpu/xeon/gmc + pushd CodeGen/kubernetes/gmc install_codegen popd ;; validate_CodeGen) - pushd CodeGen/kubernetes/intel/cpu/xeon/gmc + pushd CodeGen/kubernetes/gmc validate_codegen popd ;; diff --git a/README.md b/README.md index b04ffbe6c..7d86ddbdb 100644 --- a/README.md +++ b/README.md @@ -43,19 +43,19 @@ Deployment are based on released docker images by default, check [docker image l #### Deploy Examples -| Use Case | Docker Compose
Deployment on Xeon | Docker Compose
Deployment on Gaudi | Kubernetes with Manifests | Kubernetes with Helm Charts | Kubernetes with GMC | -| ----------------- | ------------------------------------------------------------------------------ | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | -| ChatQnA | [Xeon Instructions](ChatQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](ChatQnA/docker_compose/intel/hpu/gaudi/README.md) | [ChatQnA with Manifests](ChatQnA/kubernetes/intel/README.md) | [ChatQnA with Helm Charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/chatqna/README.md) | [ChatQnA with GMC](ChatQnA/kubernetes/intel/README_gmc.md) | -| CodeGen | [Xeon Instructions](CodeGen/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](CodeGen/docker_compose/intel/hpu/gaudi/README.md) | [CodeGen with Manifests](CodeGen/kubernetes/intel/README.md) | [CodeGen with Helm Charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codegen/README.md) | [CodeGen with GMC](CodeGen/kubernetes/intel/README_gmc.md) | -| CodeTrans | [Xeon Instructions](CodeTrans/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](CodeTrans/docker_compose/intel/hpu/gaudi/README.md) | [CodeTrans with Manifests](CodeTrans/kubernetes/intel/README.md) | [CodeTrans with Helm Charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codetrans/README.md) | [CodeTrans with GMC](CodeTrans/kubernetes/intel/README_gmc.md) | -| DocSum | [Xeon Instructions](DocSum/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](DocSum/docker_compose/intel/hpu/gaudi/README.md) | [DocSum with Manifests](DocSum/kubernetes/intel/README.md) | [DocSum with Helm Charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/docsum/README.md) | [DocSum with GMC](DocSum/kubernetes/intel/README_gmc.md) | -| SearchQnA | [Xeon Instructions](SearchQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](SearchQnA/docker_compose/intel/hpu/gaudi/README.md) | Not Supported | Not Supported | [SearchQnA with GMC](SearchQnA/kubernetes/intel/README_gmc.md) | -| FaqGen | [Xeon Instructions](FaqGen/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](FaqGen/docker_compose/intel/hpu/gaudi/README.md) | [FaqGen with Manifests](FaqGen/kubernetes/intel/README.md) | Not Supported | [FaqGen with GMC](FaqGen/kubernetes/intel/README_gmc.md) | -| Translation | [Xeon Instructions](Translation/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](Translation/docker_compose/intel/hpu/gaudi/README.md) | [Translation with Manifests](Translation/kubernetes/intel/README.md) | Not Supported | [Translation with GMC](Translation/kubernetes/intel/README_gmc.md) | -| AudioQnA | [Xeon Instructions](AudioQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](AudioQnA/docker_compose/intel/hpu/gaudi/README.md) | [AudioQnA with Manifests](AudioQnA/kubernetes/intel/README.md) | Not Supported | [AudioQnA with GMC](AudioQnA/kubernetes/intel/README_gmc.md) | -| VisualQnA | [Xeon Instructions](VisualQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](VisualQnA/docker_compose/intel/hpu/gaudi/README.md) | [VisualQnA with Manifests](VisualQnA/kubernetes/intel/README.md) | Not Supported | [VisualQnA with GMC](VisualQnA/kubernetes/intel/README_gmc.md) | -| MultimodalQnA | [Xeon Instructions](MultimodalQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md) | Not supported | Not supported | Not supported | -| ProductivitySuite | [Xeon Instructions](ProductivitySuite/docker_compose/intel/cpu/xeon/README.md) | Not Supported | [ProductivitySuite with Manifests](ProductivitySuite/kubernetes/intel/README.md) | Not Supported | Not Supported | +| Use Case | Docker Compose
Deployment on Xeon | Docker Compose
Deployment on Gaudi | Kubernetes with Helm Charts | Kubernetes with GMC | +| ----------------- | ------------------------------------------------------------------------------ | ---------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------ | +| ChatQnA | [Xeon Instructions](ChatQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](ChatQnA/docker_compose/intel/hpu/gaudi/README.md) | [ChatQnA with Helm Charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/chatqna/README.md) | [ChatQnA with GMC](ChatQnA/kubernetes/intel/README_gmc.md) | +| CodeGen | [Xeon Instructions](CodeGen/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](CodeGen/docker_compose/intel/hpu/gaudi/README.md) | [CodeGen with Helm Charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codegen/README.md) | [CodeGen with GMC](CodeGen/kubernetes/gmc/README.md) | +| CodeTrans | [Xeon Instructions](CodeTrans/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](CodeTrans/docker_compose/intel/hpu/gaudi/README.md) | [CodeTrans with Helm Charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codetrans/README.md) | [CodeTrans with GMC](CodeTrans/kubernetes/intel/README_gmc.md) | +| DocSum | [Xeon Instructions](DocSum/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](DocSum/docker_compose/intel/hpu/gaudi/README.md) | [DocSum with Helm Charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/docsum/README.md) | [DocSum with GMC](DocSum/kubernetes/intel/README_gmc.md) | +| SearchQnA | [Xeon Instructions](SearchQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](SearchQnA/docker_compose/intel/hpu/gaudi/README.md) | Not Supported | [SearchQnA with GMC](SearchQnA/kubernetes/intel/README_gmc.md) | +| FaqGen | [Xeon Instructions](FaqGen/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](FaqGen/docker_compose/intel/hpu/gaudi/README.md) | Not Supported | [FaqGen with GMC](FaqGen/kubernetes/intel/README_gmc.md) | +| Translation | [Xeon Instructions](Translation/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](Translation/docker_compose/intel/hpu/gaudi/README.md) | Not Supported | [Translation with GMC](Translation/kubernetes/intel/README_gmc.md) | +| AudioQnA | [Xeon Instructions](AudioQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](AudioQnA/docker_compose/intel/hpu/gaudi/README.md) | Not Supported | [AudioQnA with GMC](AudioQnA/kubernetes/intel/README_gmc.md) | +| VisualQnA | [Xeon Instructions](VisualQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](VisualQnA/docker_compose/intel/hpu/gaudi/README.md) | Not Supported | [VisualQnA with GMC](VisualQnA/kubernetes/intel/README_gmc.md) | +| MultimodalQnA | [Xeon Instructions](MultimodalQnA/docker_compose/intel/cpu/xeon/README.md) | [Gaudi Instructions](MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md) | Not supported | Not supported | +| ProductivitySuite | [Xeon Instructions](ProductivitySuite/docker_compose/intel/cpu/xeon/README.md) | Not Supported | Not Supported | Not Supported | ## Supported Examples