Bump the version of openeuler/vllm-cpu to 0.10.1 (#2269)

Signed-off-by: zhihang <[email protected]>

Author: zhihangdeng

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

@@ -25,14 +25,13 @@ services:
       https_proxy: ${https_proxy}
     restart: unless-stopped
   vllm-service:
-    image: openeuler/vllm-cpu:0.9.1-oe2403lts
+    image: openeuler/vllm-cpu:0.10.1-oe2403lts
     container_name: vllm-service
     ports:
       - ${LLM_SERVER_PORT:-3006}:80
     volumes:
       - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
     shm_size: 128g
-    privileged: true
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

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

@@ -88,14 +88,13 @@ services:
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
   vllm-service:
-    image: openeuler/vllm-cpu:0.9.1-oe2403lts
+    image: openeuler/vllm-cpu:0.10.1-oe2403lts
     container_name: vllm-service
     ports:
       - "9009:80"
     volumes:
       - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
     shm_size: 128g
-    privileged: true
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

CodeGen/docker_compose/intel/cpu/xeon/compose_openeuler.yaml

@@ -4,14 +4,13 @@
 services:
 
   vllm-service:
-    image: openeuler/vllm-cpu:0.9.1-oe2403lts
+    image: openeuler/vllm-cpu:0.10.1-oe2403lts
     container_name: vllm-server
     ports:
       - "8028:80"
     volumes:
       - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
     shm_size: 1g
-    privileged: true
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}