Update TGI CPU image to latest official release 2.4.0 (#1035)

Signed-off-by: lvliang-intel <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: lvliang-intel

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"

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"

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:

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"

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

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"

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"

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"

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.

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