fix tests

Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>

Author: artem-astafev

VisualQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml

@@ -30,7 +30,7 @@ services:
     security_opt:
       - seccomp:unconfined
       - apparmor=unconfined
-    command: "--model ${VISUALQNA_LLM_MODEL_ID} --swap-space 16 --disable-log-requests --dtype float16 --tensor-parallel-size 1 --host 0.0.0.0 --port 8011 --num-scheduler-steps 1 --distributed-executor-backend \"mp\""
+    command: "--model ${VISUALQNA_LVM_MODEL_ID} --swap-space 16 --disable-log-requests --dtype float16 --tensor-parallel-size 1 --host 0.0.0.0 --port 8011 --num-scheduler-steps 1 --distributed-executor-backend \"mp\""
     ipc: host
   lvm:
     image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
@@ -46,7 +46,7 @@ services:
       https_proxy: ${https_proxy}
       LVM_COMPONENT_NAME: "OPEA_VLLM_LVM"
       LVM_ENDPOINT: ${LVM_ENDPOINT}
-      LLM_MODEL_ID: ${VISUALQNA_LLM_MODEL_ID}
+      LLM_MODEL_ID: ${VISUALQNA_LVM_MODEL_ID}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     restart: unless-stopped

VisualQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh

@@ -9,7 +9,7 @@ export VISUALQNA_VLLM_SERVICE_PORT="8081"
 export VISUALQNA_HUGGINGFACEHUB_API_TOKEN=${Your_HUGGINGFACEHUB_API_TOKEN}
 export VISUALQNA_CARD_ID="card1"
 export VISUALQNA_RENDER_ID="renderD136"
-export VISUALQNA_LLM_MODEL_ID="Xkev/Llama-3.2V-11B-cot"
+export VISUALQNA_LVM_MODEL_ID="Xkev/Llama-3.2V-11B-cot"
 export LVM_ENDPOINT="http://${HOST_IP}:${VISUALQNA_VLLM_SERVICE_PORT}"
 export LVM_SERVICE_PORT=9399
 export MEGA_SERVICE_HOST_IP=${HOST_IP}