1、创建docker容器
创建vim docker_run.sh内容如下
镜像：vllm-ascend:v0.13.0rc3-a3
export IMAGE=quay.io/ascend/vllm-ascend:v0.13.0rc3-a3 export NAME=deepseekV4-sj docker run --rm \ --name $NAME \ --net=host \ --shm-size=1g \ --device /dev/davinci0 \ --device /dev/davinci1 \ --device /dev/davinci2 \ --device /dev/davinci3 \ --device /dev/davinci4 \ --device /dev/davinci5 \ --device /dev/davinci6 \ --device /dev/davinci7 \ --device /dev/davinci8 \ --device /dev/davinci9 \ --device /dev/davinci10 \ --device /dev/davinci11 \ --device /dev/davinci12 \ --device /dev/davinci13 \ --device /dev/davinci14 \ --device /dev/davinci15 \ --device /dev/davinci_manager \ --device /dev/devmm_svm \ --device /dev/hisi_hdc \ -v /usr/local/dcmi:/usr/local/dcmi \ -v /usr/local/Ascend/driver/tools/hccn_tool:/usr/local/Ascend/driver/tools/hccn_tool \ -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 /etc/hccn.conf:/etc/hccn.conf \ -v /mnt/sfs_turbo/.cache:/root/.cache \ -v /data:/data \ -d $IMAGE tail -f /dev/null ~给文件赋权限
chmod +x docker_run.sh
执行脚本
./docker_run.sh
使用docker ps查看创建的docker容器
使用以下命令进入容器
docker exec -it e9c600eff989 bash
2、下载模型
下载以下模型
https://www.modelscope.cn/models/Eco-Tech/DeepSeek-V4-Flash-w8a8-mtp
安装以下插件
pip install modelscope
下载到当前目录的dir文件夹中
modelscope download --model Eco-Tech/DeepSeek-V4-Flash-w8a8-mtp --local_dir ./dir
注：作者下载路径为：/data/share/models中（路径根据实际情况修改）
3、运行模型
创建运行脚本start.sh
export OMP_PROC_BIND=false export OMP_NUM_THREADS=10 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True export ACL_OP_INIT_MODE=1 export ASCEND_A3_ENABLE=1 export USE_MULTI_BLOCK_POOL=1 export HCCL_BUFFSIZE=1024 export VLLM_ASCEND_ENABLE_FUSED_MC2=1 export VLLM_ASCEND_ENABLE_FLASHCOMM1=1 vllm serve /data/share/models/DeepSeek-V4-Flash-w8a8-mtp \ --host 0.0.0.0 \ --max_model_len 152000 \ --max-num-batched-tokens 8192 \ --served-model-name deepseek_v4 \ --gpu-memory-utilization 0.9 \ --max-num-seqs 64 \ --data-parallel-size 2 \ --tensor-parallel-size 8 \ --enable-expert-parallel \ --quantization ascend \ --chat-template /data/share/models/DeepSeek-V4-Flash-w8a8-mtp/chat_template.jinja \ --port 8005 \ --block-size 128 \ --async-scheduling \ --safetensors-load-strategy eager \ --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}'\ --speculative-config '{"num_speculative_tokens": 1,"method": "deepseek_mtp"}' \ --additional-config '{"enable_cpu_binding": "true","multistream_overlap_shared_expert": false}'4、调用
使用以下命令调用（ip可根据实际情况修改）
curl http://localhost:8005/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek_v4",
"messages": [
{"role": "system", "content": "You are a helpful assistant"},
{"role": "user", "content": "你好，请介绍一下自己"}
],
"temperature": 0.7,
"max_tokens": 1024
}'
