Using TGI official release docker image for intel cpu (#581)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

CodeTrans/docker/xeon/compose.yaml

@@ -3,7 +3,7 @@
 
 services:
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:1.4
+    image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu
     container_name: codetrans-tgi-service
     ports:
       - "8008:80"
@@ -15,7 +15,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-    command: --model-id ${LLM_MODEL_ID}
+    command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
   llm:
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
     container_name: llm-tgi-server

CodeTrans/kubernetes/manifests/xeon/codetrans.yaml

@@ -41,6 +41,7 @@ metadata:
 data:
   MODEL_ID: "HuggingFaceH4/mistral-7b-grok"
   PORT: "2080"
+  CUDA_GRAPHS: "0"
   HUGGING_FACE_HUB_TOKEN: "insert-your-huggingface-token-here"
   HF_TOKEN: "insert-your-huggingface-token-here"
   MAX_INPUT_TOKENS: "1024"
@@ -229,7 +230,7 @@ spec:
                 name: codetrans-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.1.0"
+          image: "ghcr.io/huggingface/text-generation-inference:latest-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data