Update TGI CPU image to latest official release 2.4.0

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
opea-project · Oct 28, 2024 · a6d08fb · a6d08fb
1 parent bc47930
commit a6d08fb
Show file tree

Hide file tree

Showing 39 changed files with 42 additions and 42 deletions.
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml b/AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -41,7 +41,7 @@ services:
     environment:
       TTS_ENDPOINT: ${TTS_ENDPOINT}
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "3006:80"

diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml b/AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml
@@ -26,7 +26,7 @@ services:
       https_proxy: ${https_proxy}
     restart: unless-stopped
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "3006:80"

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:sha-e4201f4-intel-cpu"
+        image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:

diff --git a/AvatarChatbot/docker_compose/intel/cpu/xeon/compose.yaml b/AvatarChatbot/docker_compose/intel/cpu/xeon/compose.yaml
@@ -42,7 +42,7 @@ services:
     environment:
       TTS_ENDPOINT: ${TTS_ENDPOINT}
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "3006:80"

diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/README.md b/ChatQnA/docker_compose/intel/cpu/xeon/README.md
@@ -195,7 +195,7 @@ 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:sha-e4201f4-intel-cpu --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:2.4.0-intel-cpu --model-id $model_name
    ```
 
 2. Offline
@@ -209,7 +209,7 @@ 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:sha-e4201f4-intel-cpu --model-id /data
+     docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu --model-id /data
      ```
 
 ### Setup Environment Variables

diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -73,7 +73,7 @@ services:
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "9009:80"

diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml
@@ -72,7 +72,7 @@ services:
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "6042:80"

diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml
@@ -57,7 +57,7 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "9009:80"

diff --git a/ChatQnA/kubernetes/intel/README_gmc.md b/ChatQnA/kubernetes/intel/README_gmc.md
@@ -18,7 +18,7 @@ The ChatQnA uses the below prebuilt images if you choose a Xeon deployment
 - tei_embedding_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
 - retriever: opea/retriever-redis:latest
 - tei_xeon_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-- tgi-service: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+- tgi-service: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
 - chaqna-xeon-backend-server: opea/chatqna:latest
 
 Should you desire to use the Gaudi accelerator, two alternate images are used for the embedding and llm services.

diff --git a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml
@@ -1100,7 +1100,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data
@@ -1180,7 +1180,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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
@@ -922,7 +922,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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
@@ -925,7 +925,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/ChatQnA/tests/test_compose_on_xeon.sh b/ChatQnA/tests/test_compose_on_xeon.sh
@@ -22,7 +22,7 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui chatqna-conversation-ui dataprep-redis retriever-redis nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
 
     docker images && sleep 1s

diff --git a/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml b/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
@@ -3,7 +3,7 @@
 
 services:
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "8028:80"

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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml
@@ -126,7 +126,7 @@ spec:
             - name: no_proxy
               value:
           securityContext: {}
-          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/CodeGen/tests/test_compose_on_xeon.sh b/CodeGen/tests/test_compose_on_xeon.sh
@@ -22,7 +22,7 @@ function build_docker_images() {
     service_list="codegen codegen-ui llm-tgi"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     docker images && sleep 1s
 }
 

diff --git a/CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml b/CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml
@@ -3,7 +3,7 @@
 
 services:
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: codetrans-tgi-service
     ports:
       - "8008:80"

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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/CodeTrans/tests/test_compose_on_xeon.sh b/CodeTrans/tests/test_compose_on_xeon.sh
@@ -22,7 +22,7 @@ function build_docker_images() {
     service_list="codetrans codetrans-ui llm-tgi nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     docker images && sleep 1s
 }
 

diff --git a/DocSum/docker_compose/intel/cpu/xeon/compose.yaml b/DocSum/docker_compose/intel/cpu/xeon/compose.yaml
@@ -3,7 +3,7 @@
 
 services:
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "8008:80"

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:sha-e4201f4-intel-cpu`. The service is called tgi-svc. Meanwhile, the Gaudi version launches the
+the image `ghcr.io/huggingface/text-generation-inference:2.4.0-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:2.0.5`. 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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/DocSum/kubernetes/intel/cpu/xeon/manifest/ui/react-docsum.yaml b/DocSum/kubernetes/intel/cpu/xeon/manifest/ui/react-docsum.yaml
@@ -126,7 +126,7 @@ spec:
             - name: no_proxy
               value:
           securityContext: {}
-          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/FaqGen/docker_compose/intel/cpu/xeon/compose.yaml b/FaqGen/docker_compose/intel/cpu/xeon/compose.yaml
@@ -3,7 +3,7 @@
 
 services:
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-xeon-server
     ports:
       - "8008:80"

diff --git a/FaqGen/kubernetes/intel/cpu/xeon/manifest/faqgen_react_ui.yaml b/FaqGen/kubernetes/intel/cpu/xeon/manifest/faqgen_react_ui.yaml
@@ -126,7 +126,7 @@ spec:
             - name: no_proxy
               value:
           securityContext: {}
-          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml b/SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -73,7 +73,7 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "3006:80"

diff --git a/SearchQnA/tests/test_compose_on_xeon.sh b/SearchQnA/tests/test_compose_on_xeon.sh
@@ -23,7 +23,7 @@ function build_docker_images() {
     docker compose -f build.yaml build ${service_list} --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:sha-e4201f4-intel-cpu
+    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     docker images && sleep 1s
 }
 

diff --git a/Translation/docker_compose/intel/cpu/xeon/compose.yaml b/Translation/docker_compose/intel/cpu/xeon/compose.yaml
@@ -3,7 +3,7 @@
 
 services:
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-service
     ports:
       - "8008:80"

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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/Translation/tests/test_compose_on_xeon.sh b/Translation/tests/test_compose_on_xeon.sh
@@ -22,7 +22,7 @@ function build_docker_images() {
     service_list="translation translation-ui llm-tgi nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     docker images && sleep 1s
 }
 

diff --git a/VisualQnA/docker_compose/intel/cpu/xeon/README.md b/VisualQnA/docker_compose/intel/cpu/xeon/README.md
@@ -67,12 +67,12 @@ docker build --no-cache -t opea/visualqna-ui:latest --build-arg https_proxy=$htt
 ### 4. Pull TGI Xeon Image
 
 ```bash
-docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
 ```
 
 Then run the command `docker images`, you will have the following 5 Docker Images:
 
-1. `ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu`
+1. `ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu`
 2. `opea/lvm-tgi:latest`
 3. `opea/visualqna:latest`
 4. `opea/visualqna-ui:latest`

diff --git a/VisualQnA/docker_compose/intel/cpu/xeon/compose.yaml b/VisualQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -3,7 +3,7 @@
 
 services:
   llava-tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-llava-xeon-server
     ports:
       - "8399:80"

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:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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:sha-e4201f4-intel-cpu
+    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     docker images && sleep 1s
 }