Use vllm release image for AudioQnA and ChatQnA. (#2239)

ZePan110 · web-flow · commit e8e1564ddea9 · 2025-09-08T14:45:22.000+08:00
Signed-off-by: ZePan110 &lt;ze.pan@intel.com&gt;
diff --git a/AudioQnA/docker_compose/amd/cpu/epyc/compose.yaml b/AudioQnA/docker_compose/amd/cpu/epyc/compose.yaml
@@ -26,7 +26,7 @@ services:
       https_proxy: ${https_proxy}
     restart: unless-stopped
   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:
       - ${LLM_SERVER_PORT:-3006}:80
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml b/AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -25,7 +25,7 @@ services:
       https_proxy: ${https_proxy}
     restart: unless-stopped
   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:
       - ${LLM_SERVER_PORT:-3006}:80
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml b/AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml
@@ -29,7 +29,7 @@ services:
     #  - ./pretrained_models/:/home/user/GPT-SoVITS/GPT_SoVITS/pretrained_models/
     restart: unless-stopped
   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:
       - ${LLM_SERVER_PORT:-3006}:80
diff --git a/AudioQnA/docker_image_build/build.yaml b/AudioQnA/docker_image_build/build.yaml
@@ -73,12 +73,6 @@ services:
       dockerfile: comps/third_parties/gpt-sovits/src/Dockerfile
     extends: audioqna
     image: ${REGISTRY:-opea}/gpt-sovits:${TAG:-latest}
-  vllm:
-    build:
-      context: vllm
-      dockerfile: docker/Dockerfile.cpu
-    extends: audioqna
-    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
   vllm-gaudi:
     build:
       context: vllm-fork
diff --git a/AudioQnA/tests/test_compose_multilang_on_xeon.sh b/AudioQnA/tests/test_compose_multilang_on_xeon.sh
@@ -25,14 +25,8 @@ 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 && cd ../
-
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="audioqna-multilang audioqna-ui whisper gpt-sovits vllm"
+    service_list="audioqna-multilang audioqna-ui whisper gpt-sovits"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1s
diff --git a/AudioQnA/tests/test_compose_on_epyc.sh b/AudioQnA/tests/test_compose_on_epyc.sh
@@ -27,20 +27,8 @@ 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 ${VLLM_VER} &>/dev/null
-	VLLM_REQ_FILE="requirements/cpu.txt"
-	if ! grep -q "^transformers" "$VLLM_REQ_FILE"; then
-		echo "Adding transformers<4.54.0 to $VLLM_REQ_FILE"
-		echo "transformers<4.54.0" >>"$VLLM_REQ_FILE"
-	fi
-	cd ../
-
 	echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-	service_list="audioqna audioqna-ui whisper speecht5 vllm"
+	service_list="audioqna audioqna-ui whisper speecht5"
 	docker compose -f build.yaml build ${service_list} --no-cache >${LOG_PATH}/docker_image_build.log
 
 	docker images && sleep 1s
diff --git a/AudioQnA/tests/test_compose_on_xeon.sh b/AudioQnA/tests/test_compose_on_xeon.sh
@@ -25,14 +25,8 @@ 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 && cd ../
-
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="audioqna audioqna-ui whisper speecht5 vllm"
+    service_list="audioqna audioqna-ui whisper speecht5"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1s
diff --git a/ChatQnA/docker_compose/amd/cpu/epyc/compose.yaml b/ChatQnA/docker_compose/amd/cpu/epyc/compose.yaml
@@ -90,7 +90,7 @@ 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/ChatQnA/docker_compose/amd/cpu/epyc/compose_faqgen.yaml b/ChatQnA/docker_compose/amd/cpu/epyc/compose_faqgen.yaml
@@ -83,7 +83,7 @@ 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-server
     ports:
       - ${LLM_ENDPOINT_PORT:-9009}:80
diff --git a/ChatQnA/docker_compose/amd/cpu/epyc/compose_milvus.yaml b/ChatQnA/docker_compose/amd/cpu/epyc/compose_milvus.yaml
@@ -147,7 +147,7 @@ services:
     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/ChatQnA/docker_compose/amd/cpu/epyc/compose_pinecone.yaml b/ChatQnA/docker_compose/amd/cpu/epyc/compose_pinecone.yaml
@@ -77,7 +77,7 @@ 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/ChatQnA/docker_compose/amd/cpu/epyc/compose_qdrant.yaml b/ChatQnA/docker_compose/amd/cpu/epyc/compose_qdrant.yaml
@@ -83,7 +83,7 @@ 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:
       - "6042:80"
diff --git a/ChatQnA/docker_compose/amd/cpu/epyc/compose_without_rerank.yaml b/ChatQnA/docker_compose/amd/cpu/epyc/compose_without_rerank.yaml
@@ -67,7 +67,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
   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/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -89,7 +89,7 @@ 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/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml
@@ -81,7 +81,7 @@ 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-server
     ports:
       - ${LLM_ENDPOINT_PORT:-9009}:80
diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_mariadb.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_mariadb.yaml
@@ -90,7 +90,7 @@ 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/ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml
@@ -144,7 +144,7 @@ services:
     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/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml
@@ -76,7 +76,7 @@ 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/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml
@@ -81,7 +81,7 @@ 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:
       - "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
@@ -65,7 +65,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
   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/ChatQnA/docker_image_build/build.yaml b/ChatQnA/docker_image_build/build.yaml
@@ -114,12 +114,6 @@ services:
       context: GenAIComps
       dockerfile: comps/third_parties/vllm/src/Dockerfile.amd_gpu
     image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
-  vllm:
-    build:
-      context: vllm
-      dockerfile: docker/Dockerfile.cpu
-    extends: chatqna
-    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
   vllm-gaudi:
     build:
       context: vllm-fork
diff --git a/ChatQnA/tests/test_compose_faqgen_on_epyc.sh b/ChatQnA/tests/test_compose_faqgen_on_epyc.sh
@@ -25,19 +25,9 @@ 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/vllm-project/vllm.git && cd vllm
-	VLLM_VER=v0.10.0
-	echo "Check out vLLM tag ${VLLM_VER}"
-	git checkout ${VLLM_VER} &>/dev/null
-	VLLM_REQ_FILE="requirements/cpu.txt"
-	if ! grep -q "^transformers" "$VLLM_REQ_FILE"; then
-		echo "Adding transformers<4.54.0 to $VLLM_REQ_FILE"
-		echo "transformers<4.54.0" >>"$VLLM_REQ_FILE"
-	fi
-	cd ../
 
 	echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-	service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm nginx"
+	service_list="chatqna chatqna-ui dataprep retriever llm-faqgen nginx"
 	docker compose -f build.yaml build ${service_list} --no-cache >${LOG_PATH}/docker_image_build.log
 
 	docker images && sleep 1s
diff --git a/ChatQnA/tests/test_compose_faqgen_on_xeon.sh b/ChatQnA/tests/test_compose_faqgen_on_xeon.sh
@@ -23,13 +23,9 @@ 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/vllm-project/vllm.git && cd vllm
-    VLLM_VER=v0.10.0
-    echo "Check out vLLM tag ${VLLM_VER}"
-    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm nginx"
+    service_list="chatqna chatqna-ui dataprep retriever llm-faqgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1s
diff --git a/ChatQnA/tests/test_compose_faqgen_tgi_on_epyc.sh b/ChatQnA/tests/test_compose_faqgen_tgi_on_epyc.sh
@@ -25,16 +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/vllm-project/vllm.git && cd vllm
-	VLLM_VER=v0.10.0
-	echo "Check out vLLM tag ${VLLM_VER}"
-	git checkout ${VLLM_VER} &>/dev/null
-	VLLM_REQ_FILE="requirements/cpu.txt"
-	if ! grep -q "^transformers" "$VLLM_REQ_FILE"; then
-		echo "Adding transformers<4.54.0 to $VLLM_REQ_FILE"
-		echo "transformers<4.54.0" >>"$VLLM_REQ_FILE"
-	fi
-	cd ../
 
 	echo "Build all the images with --no-cache, check docker_image_build.log for details..."
 	service_list="chatqna chatqna-ui dataprep retriever llm-faqgen nginx"
diff --git a/ChatQnA/tests/test_compose_mariadb_on_xeon.sh b/ChatQnA/tests/test_compose_mariadb_on_xeon.sh
@@ -23,15 +23,9 @@ 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/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="chatqna chatqna-ui dataprep retriever vllm nginx"
+    service_list="chatqna chatqna-ui dataprep retriever nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1s
diff --git a/ChatQnA/tests/test_compose_milvus_on_epyc.sh b/ChatQnA/tests/test_compose_milvus_on_epyc.sh
@@ -26,19 +26,9 @@ 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/vllm-project/vllm.git && cd vllm
-	VLLM_VER=v0.10.0
-	echo "Check out vLLM tag ${VLLM_VER}"
-	git checkout ${VLLM_VER} &>/dev/null
-	VLLM_REQ_FILE="requirements/cpu.txt"
-	if ! grep -q "^transformers" "$VLLM_REQ_FILE"; then
-		echo "Adding transformers<4.54.0 to $VLLM_REQ_FILE"
-		echo "transformers<4.54.0" >>"$VLLM_REQ_FILE"
-	fi
-	cd ../
 
 	echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-	service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
+	service_list="chatqna chatqna-ui dataprep retriever nginx"
 	docker compose -f build.yaml build ${service_list} --no-cache >${LOG_PATH}/docker_image_build.log
 
 	docker images && sleep 1s
diff --git a/ChatQnA/tests/test_compose_milvus_on_xeon.sh b/ChatQnA/tests/test_compose_milvus_on_xeon.sh
@@ -24,15 +24,9 @@ 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/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="chatqna chatqna-ui dataprep retriever vllm nginx"
+    service_list="chatqna chatqna-ui dataprep retriever nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1s
diff --git a/ChatQnA/tests/test_compose_on_epyc.sh b/ChatQnA/tests/test_compose_on_epyc.sh
@@ -26,19 +26,9 @@ 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/vllm-project/vllm.git && cd vllm
-	VLLM_VER=v0.10.0
-	echo "Check out vLLM tag ${VLLM_VER}"
-	git checkout ${VLLM_VER} &>/dev/null
-	VLLM_REQ_FILE="requirements/cpu.txt"
-	if ! grep -q "^transformers" "$VLLM_REQ_FILE"; then
-		echo "Adding transformers<4.54.0 to $VLLM_REQ_FILE"
-		echo "transformers<4.54.0" >>"$VLLM_REQ_FILE"
-	fi
-	cd ../
 
 	echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-	service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
+	service_list="chatqna chatqna-ui dataprep retriever nginx"
 	docker compose -f build.yaml build ${service_list} --no-cache >${LOG_PATH}/docker_image_build.log
 
 	docker images && sleep 1s
diff --git a/ChatQnA/tests/test_compose_on_xeon.sh b/ChatQnA/tests/test_compose_on_xeon.sh
@@ -23,15 +23,9 @@ 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/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="chatqna chatqna-ui dataprep retriever vllm nginx"
+    service_list="chatqna chatqna-ui dataprep retriever nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1s
diff --git a/ChatQnA/tests/test_compose_pinecone_on_epyc.sh b/ChatQnA/tests/test_compose_pinecone_on_epyc.sh
@@ -26,19 +26,9 @@ 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/vllm-project/vllm.git && cd vllm
-	VLLM_VER=v0.10.0
-	echo "Check out vLLM tag ${VLLM_VER}"
-	git checkout ${VLLM_VER} &>/dev/null
-	VLLM_REQ_FILE="requirements/cpu.txt"
-	if ! grep -q "^transformers" "$VLLM_REQ_FILE"; then
-		echo "Adding transformers<4.54.0 to $VLLM_REQ_FILE"
-		echo "transformers<4.54.0" >>"$VLLM_REQ_FILE"
-	fi
-	cd ../
 
 	echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-	service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
+	service_list="chatqna chatqna-ui dataprep retriever nginx"
 	docker compose -f build.yaml build ${service_list} --no-cache >${LOG_PATH}/docker_image_build.log
 
 	docker images && sleep 1s
diff --git a/ChatQnA/tests/test_compose_pinecone_on_xeon.sh b/ChatQnA/tests/test_compose_pinecone_on_xeon.sh
diff --git a/ChatQnA/tests/test_compose_qdrant_on_epyc.sh b/ChatQnA/tests/test_compose_qdrant_on_epyc.sh
diff --git a/ChatQnA/tests/test_compose_qdrant_on_xeon.sh b/ChatQnA/tests/test_compose_qdrant_on_xeon.sh
diff --git a/ChatQnA/tests/test_compose_without_rerank_on_epyc.sh b/ChatQnA/tests/test_compose_without_rerank_on_epyc.sh
diff --git a/ChatQnA/tests/test_compose_without_rerank_on_xeon.sh b/ChatQnA/tests/test_compose_without_rerank_on_xeon.sh
