mkdir /home/model/Qwen
mkdir  /home/model/Qwen/Qwen2.5-VL-3B-Instruct
modelscope download --model Qwen/Qwen2.5-VL-3B-Instruct --local_dir /home/model/Qwen/Qwen2.5-VL-3B-Instruct

#!/bin/sh

LOCAL_MODEL_PATH=
DOCKER_IMAGE=
CONTAINER_NAME=

ASCEND_DEVICES=
SERVICE_PORT=

usage() {
    echo "Usage: $0 -m LOCAL_MODEL_PATH -n CONTAINER_NAME [-d ASCEND_DEVICES] [-p SERVICE_PORT]" 
    echo "Options:"
    echo "  -m,  Set local model path (MUST), e.g., \"/root/.cache/Qwen/Qwen3-4B\""
    echo "  -i,  Set docker image name or id (MUST)"
    echo "  -n,  Set new container name (MUST)"
    echo "  -d,  Set visiable ascend device (optional), default \"0,1,2,3,4,5,6,7\""
    echo "  -p,  Set service port (optional), default \'8000\'"
    exit 1
}
while getopts ":i:p:m:n:d:h" opt; do
    case $opt in
        p)
            SERVICE_PORT="$OPTARG"
            echo "arg -p provided, service port set with : $SERVICE_PORT"
            ;;
        m)
            LOCAL_MODEL_PATH="$OPTARG"
            echo "arg -m provided, local model path set with : $LOCAL_MODEL_PATH"
            ;;
        n)
            CONTAINER_NAME="$OPTARG"
            echo "arg -n provided, container name set with : $CONTAINER_NAME"
            ;;
        d)
            ASCEND_DEVICES="$OPTARG"
            echo "arg -d provided, ASCEND_RT_VISIBLE_DEVICES set with : $ASCEND_DEVICES"
            ;;
        i)
            DOCKER_IMAGE="$OPTARG"
            echo "arg -i provided, docker image set with : $DOCKER_IMAGE"
	    ;;
        h)
            usage
            exit 0
            ;;
        \?)
            echo "Error: invalid arg -$OPTARG" >&2
            usage
            exit 1
            ;;
        :)
            echo "Error: arg -$OPTARG needs a valule" >&2
            usage
            exit 1
            ;;
    esac
done

if [ -z $LOCAL_MODEL_PATH ] || [ -z $DOCKER_IMAGE ] || [ -z $CONTAINER_NAME ]; then
	echo "Error: required args missing"
	usage
	exit 1
fi

if [ "$SERVICE_PORT" = "" ]; then
	SERVICE_PORT=8000
fi

if [ "$ASCEND_DEVICES" = "" ]; then
	ASCEND_DEVICES="0,1,2,3,4,5,6,7"
fi

if [ "$LOCAL_CACHE_PATH" = "" ]; then
	LOCAL_CACHE_PATH="/root/.cache"
fi

MODEL_NAME=`basename $LOCAL_MODEL_PATH`

docker run -itd -u 0  --ipc=host  --privileged \
	-e VLLM_USE_MODELSCOPE=True -e PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256 \
	-e ASCEND_RT_VISIBLE_DEVICES=$ASCEND_DEVICES \
	-e SERVIC_MODEL_NAME=${MODEL_NAME} \
	--name $CONTAINER_NAME \
	--device /dev/davinci_manager \
	--device /dev/devmm_svm \
	--device /dev/hisi_hdc \
	-v /usr/local/dcmi:/usr/local/dcmi \
	-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
	-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
	-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
	-v /etc/ascend_install.info:/etc/ascend_install.info \
	-v $LOCAL_CACHE_PATH:/root/.cache \
	-v $LOCAL_MODEL_PATH:/model \
	-v /opt:/opt \
	-p $SERVICE_PORT:8000 \
	-it $DOCKER_IMAGE bash

bash  run-vllm-ascend_v1.sh -i <镜像名称> -m   <模型参数> -n  <容器实例名称>  -d <NPU设备ID> -p  <监听端口>

bash  run-vllm-ascend_v1.sh  -m /home/model/Qwen/Qwen2.5-VL-3B-Instruct -i vllm-ascend_v0.10.0rc1:v1.0_250901 -n qwen25vl3b  -p 8901 -d "0"

docker logs -f qwen25vl3b

INFO 09-02 02:48:05 [launcher.py:37] Route: /v1/rerank, Methods: POST INFO 09-02 02:48:05 [launcher.py:37] Route: /v2/rerank, Methods: POST INFO 09-02 02:48:05 [launcher.py:37] Route: /scale_elastic_ep, Methods: POST INFO 09-02 02:48:05 [launcher.py:37] Route: /is_scaling_elastic_ep, Methods: POST INFO 09-02 02:48:05 [launcher.py:37] Route: /invocations, Methods: POST INFO 09-02 02:48:05 [launcher.py:37] Route: /metrics, Methods: GET INFO: Started server process [591] INFO: Waiting for application startup. INFO: Application startup complete.