Use vllm-gaudi:1.22.0 image and add no_proxy (#2270)

ZePan110 · pre-commit-ci[bot] · web-flow · commit b3636358d3d5 · 2025-09-18T16:03:40.000+08:00
Signed-off-by: ZePan110 &lt;ze.pan@intel.com&gt;
Co-authored-by: pre-commit-ci[bot] &lt;66853113+pre-commit-ci[bot]@users.noreply.github.com&gt;
diff --git a/.github/env/_build_image.sh b/.github/env/_build_image.sh
diff --git a/.github/workflows/_build_image.yml b/.github/workflows/_build_image.yml
@@ -87,13 +87,6 @@ jobs:
         run: |
           cd ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
           docker_compose_path=${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
-          source ${{ github.workspace }}/.github/env/_build_image.sh
-          if [[ $(grep -c "vllm:" ${docker_compose_path}) != 0 ]]; then
-              git clone -b ${VLLM_VER} --single-branch https://github.com/vllm-project/vllm.git
-          fi
-          if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then
-              git clone -b ${VLLM_FORK_VER} --single-branch https://github.com/HabanaAI/vllm-fork.git
-          fi
           git clone --depth 1 --branch ${{ inputs.opea_branch }} https://github.com/opea-project/GenAIComps.git
           cd GenAIComps && git rev-parse HEAD && cd ../
 
diff --git a/.github/workflows/_trivy-scan.yml b/.github/workflows/_trivy-scan.yml
@@ -50,13 +50,6 @@ jobs:
           sudo apt-get install -y jq
       - name: Clone Required Repo
         run: |
-          source ${{ github.workspace }}/.github/env/_build_image.sh
-          if [[ "${{ inputs.image }}" == "vllm" ]]; then
-              git clone -b ${VLLM_VER} --single-branch https://github.com/vllm-project/vllm.git
-          fi
-          if [[ "${{ inputs.image }}" == "vllm-gaudi" ]]; then
-              git clone -b ${VLLM_FORK_VER} --single-branch https://github.com/HabanaAI/vllm-fork.git
-          fi
           git clone --depth 1 https://github.com/opea-project/GenAIComps.git
           cd GenAIComps && git rev-parse HEAD && cd ../
       - name: Pull Image
diff --git a/.github/workflows/daily-update-vllm-version.yml.disabled b/.github/workflows/daily-update-vllm-version.yml.disabled
diff --git a/CodeGen/tests/test_compose_on_epyc.sh b/CodeGen/tests/test_compose_on_epyc.sh
@@ -40,7 +40,7 @@ function build_docker_images() {
 function start_services() {
 	local compose_file="$1"
 	local llm_container_name="$2"
-
+	export no_proxy="localhost,127.0.0.1,$ip_address"
 	cd $WORKPATH/docker_compose/amd/cpu/epyc/
 
 	# Start Docker Containers
diff --git a/CodeGen/tests/test_compose_on_gaudi.sh b/CodeGen/tests/test_compose_on_gaudi.sh
@@ -41,7 +41,7 @@ function build_docker_images() {
 function start_services() {
     local compose_file="$1"
     local llm_container_name="$2"
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
 
     # Start Docker Containers
diff --git a/CodeGen/tests/test_compose_on_xeon.sh b/CodeGen/tests/test_compose_on_xeon.sh
@@ -38,7 +38,7 @@ function build_docker_images() {
 function start_services() {
     local compose_file="$1"
     local llm_container_name="$2"
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
 
     # Start Docker Containers
diff --git a/CodeGen/tests/test_compose_openeuler_on_xeon.sh b/CodeGen/tests/test_compose_openeuler_on_xeon.sh
@@ -38,7 +38,7 @@ function build_docker_images() {
 function start_services() {
     local compose_file="$1"
     local llm_container_name="$2"
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
 
     # Start Docker Containers
diff --git a/CodeGen/tests/test_compose_tgi_on_epyc.sh b/CodeGen/tests/test_compose_tgi_on_epyc.sh
@@ -40,7 +40,7 @@ function build_docker_images() {
 function start_services() {
 	local compose_file="$1"
 	local llm_container_name="$2"
-
+	export no_proxy="localhost,127.0.0.1,$ip_address"
 	cd $WORKPATH/docker_compose/amd/cpu/epyc/
 
 	# Start Docker Containers
diff --git a/CodeTrans/tests/test_compose_on_epyc.sh b/CodeTrans/tests/test_compose_on_epyc.sh
@@ -38,7 +38,7 @@ function build_docker_images() {
 function start_services() {
 	cd $WORKPATH/docker_compose/amd/cpu/epyc
 	export HF_TOKEN=${HF_TOKEN}
-
+	export no_proxy="localhost,127.0.0.1,$ip_address"
 	export NGINX_PORT=80
 	source set_env.sh
 
diff --git a/CodeTrans/tests/test_compose_on_gaudi.sh b/CodeTrans/tests/test_compose_on_gaudi.sh
@@ -40,6 +40,7 @@ function start_services() {
     cd $WORKPATH/docker_compose/intel
     export HF_TOKEN=${HF_TOKEN}
     export NGINX_PORT=80
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source set_env.sh
     cd hpu/gaudi
 
diff --git a/CodeTrans/tests/test_compose_on_xeon.sh b/CodeTrans/tests/test_compose_on_xeon.sh
@@ -35,7 +35,7 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/intel
     export HF_TOKEN=${HF_TOKEN}
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     export NGINX_PORT=80
     source set_env.sh
     cd cpu/xeon/
diff --git a/CodeTrans/tests/test_compose_tgi_on_epyc.sh b/CodeTrans/tests/test_compose_tgi_on_epyc.sh
@@ -39,7 +39,7 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/amd/cpu/epyc/
     export HF_TOKEN=${HF_TOKEN}
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     export NGINX_PORT=80
     source set_env.sh
 
diff --git a/CodeTrans/tests/test_compose_tgi_on_gaudi.sh b/CodeTrans/tests/test_compose_tgi_on_gaudi.sh
@@ -36,7 +36,7 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/intel
     export HF_TOKEN=${HF_TOKEN}
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     export NGINX_PORT=80
     source set_env.sh
     cd hpu/gaudi/
diff --git a/CodeTrans/tests/test_compose_tgi_on_xeon.sh b/CodeTrans/tests/test_compose_tgi_on_xeon.sh
@@ -36,7 +36,7 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/intel
     export HF_TOKEN=${HF_TOKEN}
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     export NGINX_PORT=80
     source set_env.sh
     cd cpu/xeon/
diff --git a/DBQnA/tests/test_compose_on_xeon.sh b/DBQnA/tests/test_compose_on_xeon.sh
@@ -29,6 +29,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source ./set_env.sh
 
     # Start Docker Containers
diff --git a/DeepResearchAgent/docker_compose/intel/hpu/gaudi/compose.yaml b/DeepResearchAgent/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -20,7 +20,7 @@ x-common-agent-environment:
 services:
 
   vllm-service:
-    image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
+    image: opea/vllm-gaudi:1.22.0
     container_name: vllm-gaudi-server
     ports:
       - "8000:8000"
diff --git a/DeepResearchAgent/docker_image_build/build.yaml b/DeepResearchAgent/docker_image_build/build.yaml
@@ -13,9 +13,3 @@ services:
       context: ../
       dockerfile: ./Dockerfile
     image: ${REGISTRY:-opea}/deep-research-agent:${TAG:-latest}
-  vllm-gaudi:
-    build:
-      context: vllm-fork
-      dockerfile: Dockerfile.hpu
-    extends: deep-research-agent
-    image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
diff --git a/DeepResearchAgent/tests/test_compose_on_gaudi.sh b/DeepResearchAgent/tests/test_compose_on_gaudi.sh
@@ -25,9 +25,6 @@ function build_docker_images() {
     echo "GenAIComps test commit is $(git rev-parse HEAD)"
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
-    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     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
@@ -37,6 +34,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source set_env.sh
 
     # Start Docker Containers
diff --git a/DocIndexRetriever/tests/test_compose_milvus_on_gaudi.sh b/DocIndexRetriever/tests/test_compose_milvus_on_gaudi.sh
@@ -35,6 +35,7 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source ./set_env.sh
 
     # Start Docker Containers
diff --git a/DocIndexRetriever/tests/test_compose_milvus_on_xeon.sh b/DocIndexRetriever/tests/test_compose_milvus_on_xeon.sh
@@ -35,6 +35,7 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/cpu/xeon
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source ./set_env.sh
 
     # Start Docker Containers
diff --git a/DocIndexRetriever/tests/test_compose_on_gaudi.sh b/DocIndexRetriever/tests/test_compose_on_gaudi.sh
@@ -35,6 +35,7 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source ./set_env.sh
 
     # Start Docker Containers
diff --git a/DocIndexRetriever/tests/test_compose_on_xeon.sh b/DocIndexRetriever/tests/test_compose_on_xeon.sh
@@ -35,6 +35,7 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/cpu/xeon
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source ./set_env.sh
 
     # Start Docker Containers
diff --git a/DocIndexRetriever/tests/test_compose_without_rerank_on_xeon.sh b/DocIndexRetriever/tests/test_compose_without_rerank_on_xeon.sh
@@ -39,6 +39,7 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/cpu/xeon
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source ./set_env.sh
 
     # Start Docker Containers
diff --git a/DocSum/tests/test_compose_on_epyc.sh b/DocSum/tests/test_compose_on_epyc.sh
@@ -47,6 +47,7 @@ function build_docker_images() {
 
 function start_services() {
 	cd $WORKPATH/docker_compose/amd/cpu/epyc/
+	export no_proxy="localhost,127.0.0.1,$ip_address"
 	docker compose -f compose.yaml up -d >${LOG_PATH}/start_services_with_compose.log
 	sleep 1m
 }
diff --git a/DocSum/tests/test_compose_on_gaudi.sh b/DocSum/tests/test_compose_on_gaudi.sh
@@ -59,6 +59,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 2m
 }
diff --git a/DocSum/tests/test_compose_on_xeon.sh b/DocSum/tests/test_compose_on_xeon.sh
@@ -45,6 +45,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 1m
 }
diff --git a/DocSum/tests/test_compose_tgi_on_epyc.sh b/DocSum/tests/test_compose_tgi_on_epyc.sh
@@ -47,6 +47,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/cpu/epyc/
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 1m
 }
diff --git a/DocSum/tests/test_compose_tgi_on_gaudi.sh b/DocSum/tests/test_compose_tgi_on_gaudi.sh
@@ -45,6 +45,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 1m
 }
diff --git a/DocSum/tests/test_compose_tgi_on_xeon.sh b/DocSum/tests/test_compose_tgi_on_xeon.sh
@@ -45,6 +45,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 1m
 }
diff --git a/FinanceAgent/docker_compose/intel/hpu/gaudi/compose.yaml b/FinanceAgent/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -24,7 +24,7 @@ x-common-agent-environment:
 services:
 
   vllm-service:
-    image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
+    image: opea/vllm-gaudi:1.22.0
     container_name: vllm-gaudi-server
     ports:
       - "8086:8000"
diff --git a/GraphRAG/tests/test_compose_on_gaudi.sh b/GraphRAG/tests/test_compose_on_gaudi.sh
@@ -35,7 +35,7 @@ function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
     source set_env.sh
     unset OPENAI_API_KEY
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     # Start Docker Containers
     docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
 
diff --git a/HybridRAG/docker_compose/intel/hpu/gaudi/compose.yaml b/HybridRAG/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -140,7 +140,7 @@ services:
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
   vllm-service:
-    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
+    image: public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.10.1
     container_name: vllm-service
     ports:
       - "9009:80"
diff --git a/HybridRAG/docker_image_build/build.yaml b/HybridRAG/docker_image_build/build.yaml
@@ -19,12 +19,6 @@ services:
       dockerfile:  comps/text2cypher/src/Dockerfile.intel_hpu
     extends: hybridrag
     image: ${REGISTRY:-opea}/text2cypher-gaudi:${TAG:-latest}
-  vllm:
-    build:
-      context: vllm
-      dockerfile: docker/Dockerfile.cpu
-    extends: hybridrag
-    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
   dataprep:
     build:
       context: GenAIComps
diff --git a/HybridRAG/tests/test_compose_on_gaudi.sh b/HybridRAG/tests/test_compose_on_gaudi.sh
@@ -27,24 +27,16 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
 
-    git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER=v0.10.0
-
-    echo "Check out vLLM tag ${VLLM_VER}"
-    git checkout ${VLLM_VER} &> /dev/null
-    # make sure NOT change the pwd
-    cd ../
-
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="hybridrag hybridrag-ui dataprep retriever text2cypher-gaudi vllm nginx"
+    service_list="hybridrag hybridrag-ui dataprep retriever text2cypher-gaudi nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 2>&1
 
     docker images && sleep 1s
 }
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     # Start Docker Containers
     docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0
diff --git a/MultimodalQnA/tests/test_compose_milvus_on_epyc.sh b/MultimodalQnA/tests/test_compose_milvus_on_epyc.sh
@@ -73,6 +73,7 @@ function setup_env() {
 function start_services() {
     echo "Starting services..."
     cd $WORKPATH/docker_compose/amd/cpu/epyc
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose_milvus.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 2m
     echo "Services started."
diff --git a/MultimodalQnA/tests/test_compose_milvus_on_xeon.sh b/MultimodalQnA/tests/test_compose_milvus_on_xeon.sh
@@ -71,6 +71,7 @@ function setup_env() {
 function start_services() {
     echo "Starting services..."
     cd $WORKPATH/docker_compose/intel/cpu/xeon
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose_milvus.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 2m
     echo "Services started."
diff --git a/MultimodalQnA/tests/test_compose_on_epyc.sh b/MultimodalQnA/tests/test_compose_on_epyc.sh
@@ -72,6 +72,7 @@ function setup_env() {
 function start_services() {
     echo "Starting services..."
     cd $WORKPATH/docker_compose/amd/cpu/epyc
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 2m
     echo "Services started."
diff --git a/MultimodalQnA/tests/test_compose_on_gaudi.sh b/MultimodalQnA/tests/test_compose_on_gaudi.sh
@@ -67,7 +67,7 @@ function setup_env() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     # Start Docker Containers
     docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 1m
diff --git a/MultimodalQnA/tests/test_compose_on_xeon.sh b/MultimodalQnA/tests/test_compose_on_xeon.sh
@@ -70,6 +70,7 @@ function setup_env() {
 function start_services() {
     echo "Starting services..."
     cd $WORKPATH/docker_compose/intel/cpu/xeon
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     sleep 2m
     echo "Services started."
diff --git a/MultimodalQnA/tests/test_compose_vllm_on_rocm.sh b/MultimodalQnA/tests/test_compose_vllm_on_rocm.sh
@@ -44,6 +44,7 @@ function setup_env() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     docker compose -f compose_vllm.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0
     until [[ "$n" -ge 100 ]]; do
diff --git a/SearchQnA/tests/test_compose_on_epyc.sh b/SearchQnA/tests/test_compose_on_epyc.sh
@@ -39,6 +39,7 @@ function start_services() {
     export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:3008/v1/searchqna"
     export host_ip=${ip_address}
     export LOGFLAG=true
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source ./set_env.sh
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
diff --git a/SearchQnA/tests/test_compose_on_gaudi.sh b/SearchQnA/tests/test_compose_on_gaudi.sh
@@ -38,6 +38,7 @@ function start_services() {
     export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:3008/v1/searchqna"
     export host_ip=${ip_address}
     export LOGFLAG=true
+    export no_proxy="localhost,127.0.0.1,$ip_address"
     source ./set_env.sh
     cd hpu/gaudi
 
diff --git a/SearchQnA/tests/test_compose_on_xeon.sh b/SearchQnA/tests/test_compose_on_xeon.sh
diff --git a/Translation/tests/test_compose_on_epyc.sh b/Translation/tests/test_compose_on_epyc.sh
diff --git a/Translation/tests/test_compose_on_gaudi.sh b/Translation/tests/test_compose_on_gaudi.sh
diff --git a/Translation/tests/test_compose_on_xeon.sh b/Translation/tests/test_compose_on_xeon.sh
diff --git a/VideoQnA/tests/test_compose_on_xeon.sh b/VideoQnA/tests/test_compose_on_xeon.sh
diff --git a/VisualQnA/tests/test_compose_on_epyc.sh b/VisualQnA/tests/test_compose_on_epyc.sh
diff --git a/VisualQnA/tests/test_compose_on_xeon.sh b/VisualQnA/tests/test_compose_on_xeon.sh
diff --git a/VisualQnA/tests/test_compose_tgi_on_epyc.sh b/VisualQnA/tests/test_compose_tgi_on_epyc.sh
diff --git a/VisualQnA/tests/test_compose_tgi_on_gaudi.sh b/VisualQnA/tests/test_compose_tgi_on_gaudi.sh
diff --git a/VisualQnA/tests/test_compose_tgi_on_xeon.sh b/VisualQnA/tests/test_compose_tgi_on_xeon.sh
