【-it交互式启动容器】
docker run -it --gpus all --network=host --ipc=host --rm --name qwen3.5-test \
-v /home/vllm-models/Qwen3___5-35B-A3B:/home/vllm-models/Qwen3___5-35B-A3B \
-v /etc/localtime:/etc/localtime:ro \
-v /etc/timezone:/etc/timezone:ro \
--entrypoint /bin/bash \
vllm/vllm-openai
【-d后台式启动容器】
docker run -d --gpus all --network=host --ipc=host --rm --name qwen3.5-test \
-v /home/vllm-models/Qwen3___5-35B-A3B:/home/vllm-models/Qwen3___5-35B-A3B \
-v /etc/localtime:/etc/localtime:ro \
-v /etc/timezone:/etc/timezone:ro \
--entrypoint /bin/bash \
vllm/vllm-openai