Update vLLM version to v0.10.0 (#2061)

Signed-off-by: CICD-at-OPEA <[email protected]>
Co-authored-by: chen, suyue <[email protected]>

Author: CICD-at-OPEA

.github/env/_build_image.sh

@@ -2,5 +2,5 @@
 # Copyright (C) 2025 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-export VLLM_VER=v0.9.0.1
+export VLLM_VER=v0.10.0
 export VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0

AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml

@@ -40,6 +40,7 @@ services:
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}
+      VLLM_CPU_OMP_THREADS_BIND: all
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:${LLM_SERVER_PORT}/health || exit 1"]
       interval: 10s

AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml

@@ -44,6 +44,7 @@ services:
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}
+      VLLM_CPU_OMP_THREADS_BIND: all
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:${LLM_SERVER_PORT}/health || exit 1"]
       interval: 10s

AudioQnA/tests/test_compose_multilang_on_xeon.sh

@@ -27,7 +27,7 @@ function build_docker_images() {
 
     git clone https://github.com/vllm-project/vllm.git
     cd ./vllm/
-    VLLM_VER=v0.9.0.1
+    VLLM_VER=v0.10.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null && cd ../
 

AudioQnA/tests/test_compose_on_xeon.sh

@@ -27,7 +27,7 @@ function build_docker_images() {
 
     git clone https://github.com/vllm-project/vllm.git
     cd ./vllm/
-    VLLM_VER=v0.9.0.1
+    VLLM_VER=v0.10.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null && cd ../
 

ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml

@@ -83,6 +83,7 @@ services:
   vllm-service:
     image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
     container_name: vllm-server
+    privileged: true
     ports:
       - ${LLM_ENDPOINT_PORT:-9009}:80
     volumes:

ChatQnA/tests/test_compose_faqgen_on_xeon.sh

@@ -24,7 +24,7 @@ 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=v0.9.0.1
+    VLLM_VER=v0.10.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null && cd ../
 

ChatQnA/tests/test_compose_faqgen_tgi_on_xeon.sh

@@ -24,7 +24,7 @@ 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=v0.9.0.1
+    VLLM_VER=v0.10.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null && cd ../
 

ChatQnA/tests/test_compose_mariadb_on_xeon.sh

@@ -24,7 +24,7 @@ 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=v0.9.0.1
+    VLLM_VER=v0.10.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     # make sure NOT change the pwd

ChatQnA/tests/test_compose_milvus_on_xeon.sh

@@ -25,7 +25,7 @@ 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=v0.9.0.1
+    VLLM_VER=v0.10.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     # make sure NOT change the pwd