using ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel…

…-cpu as the tgi image on xeon. Signed-off-by: zhlsunshine <huailong.zhang@intel.com>
opea-project · Sep 19, 2024 · c1b24d8 · c1b24d8
1 parent c0190bb
commit c1b24d8
Show file tree

Hide file tree

Showing 18 changed files with 21 additions and 21 deletions.
diff --git a/AudioQnA/kubernetes/intel/cpu/xeon/manifest/audioqna.yaml b/AudioQnA/kubernetes/intel/cpu/xeon/manifest/audioqna.yaml
@@ -247,7 +247,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: audio-qna-config
-        image: ghcr.io/huggingface/text-generation-inference:2.2.0
+        image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:

diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/README.md b/ChatQnA/docker_compose/intel/cpu/xeon/README.md
@@ -248,7 +248,7 @@ For users in China who are unable to download models directly from Huggingface,
    export HF_TOKEN=${your_hf_token}
    export HF_ENDPOINT="https://hf-mirror.com"
    model_name="Intel/neural-chat-7b-v3-3"
-   docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.2.0 --model-id $model_name
+   docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --shm-size 1g ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu --model-id $model_name
    ```
 
 2. Offline
@@ -262,7 +262,7 @@ For users in China who are unable to download models directly from Huggingface,
      ```bash
      export HF_TOKEN=${your_hf_token}
      export model_path="/path/to/model"
-     docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.2.0 --model-id /data
+     docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu --model-id /data
      ```
 
 ### Setup Environment Variables

diff --git a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml
@@ -1497,7 +1497,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data
@@ -1577,7 +1577,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml
@@ -1319,7 +1319,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna_bf16.yaml b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna_bf16.yaml
@@ -1322,7 +1322,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml
@@ -404,7 +404,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0" 
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/CodeTrans/kubernetes/intel/cpu/xeon/manifest/codetrans.yaml b/CodeTrans/kubernetes/intel/cpu/xeon/manifest/codetrans.yaml
@@ -404,7 +404,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/DocSum/kubernetes/intel/README_gmc.md b/DocSum/kubernetes/intel/README_gmc.md
@@ -8,7 +8,7 @@ Install GMC in your Kubernetes cluster, if you have not already done so, by foll
 The DocSum application is defined as a Custom Resource (CR) file that the above GMC operator acts upon. It first checks if the microservices listed in the CR yaml file are running, if not it starts them and then proceeds to connect them. When the DocSum RAG pipeline is ready, the service endpoint details are returned, letting you use the application. Should you use "kubectl get pods" commands you will see all the component microservices, in particular embedding, retriever, rerank, and llm.
 
 The DocSum pipeline uses  prebuilt images. The Xeon version uses the prebuilt image `llm-docsum-tgi:latest` which internally leverages the
-the image `ghcr.io/huggingface/text-generation-inference:2.2.0`. The service is called tgi-svc. Meanwhile, the Gaudi version launches the
+the image `ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu`. The service is called tgi-svc. Meanwhile, the Gaudi version launches the
 service tgi-gaudi-svc, which uses the image `ghcr.io/huggingface/tgi-gaudi:2.0.1`. Both TGI model services serve the model specified in the LLM_MODEL_ID variable that is exported by you. In the below example we use `Intel/neural-chat-7b-v3-3`.
 
 [NOTE]

diff --git a/DocSum/kubernetes/intel/cpu/xeon/manifest/docsum.yaml b/DocSum/kubernetes/intel/cpu/xeon/manifest/docsum.yaml
@@ -404,7 +404,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml
@@ -113,7 +113,7 @@ services:
       LANGCHAIN_PROJECT: "opea-reranking-service"
     restart: unless-stopped
   tgi_service:
-    image: ghcr.io/huggingface/text-generation-inference:2.1.0
+    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
     container_name: tgi-service
     ports:
       - "9009:80"
@@ -174,7 +174,7 @@ services:
     ipc: host
     restart: always
   tgi_service_codegen:
-    image: ghcr.io/huggingface/text-generation-inference:2.1.0
+    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
     container_name: tgi_service_codegen
     ports:
       - "8028:80"

diff --git a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml
@@ -993,7 +993,7 @@ spec:
                 name: chatqna-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml
@@ -229,7 +229,7 @@ spec:
                 name: codegen-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/docsum.yaml b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/docsum.yaml
@@ -229,7 +229,7 @@ spec:
                 name: docsum-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/faqgen.yaml b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/faqgen.yaml
@@ -138,7 +138,7 @@ spec:
             - configMapRef:
                 name: faqgen-tgi-config
           securityContext: {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/ProductivitySuite/tests/test_compose_on_xeon.sh b/ProductivitySuite/tests/test_compose_on_xeon.sh
@@ -22,7 +22,7 @@ function build_docker_images() {
     docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-    docker pull ghcr.io/huggingface/text-generation-inference:2.1.0
+    docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
     docker images && sleep 1s
 }
 

diff --git a/Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml b/Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml
@@ -361,7 +361,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/VisualQnA/kubernetes/intel/cpu/xeon/manifest/visualqna.yaml b/VisualQnA/kubernetes/intel/cpu/xeon/manifest/visualqna.yaml
@@ -216,7 +216,7 @@ spec:
                 name: visualqna-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/VisualQnA/tests/test_compose_on_xeon.sh b/VisualQnA/tests/test_compose_on_xeon.sh
@@ -21,7 +21,7 @@ function build_docker_images() {
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:2.2.0
+    docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu 
     docker images && sleep 1s
 }