mkdir -p "${HF_HUB_CACHE:-${HF_HOME:-${XDG_CACHE_HOME:-$HOME/.cache}/huggingface}/hub}" && docker --host unix:///var/run/docker.sock run --rm --ipc=host --gpus '"device=0,1,2,3"' -e CUDA_DEVICE_ORDER=PCI_BUS_ID -e VLLM_NO_USAGE_STATS=1 -e DO_NOT_TRACK=1 -p 127.0.0.1:8000:8000 --mount "type=bind,src=${HF_HUB_CACHE:-${HF_HOME:-${XDG_CACHE_HOME:-$HOME/.cache}/huggingface}/hub},dst=/root/.cache/huggingface/hub" vllm/vllm-openai:v0.30.0 Qwen/Qwen3-8B-AWQ --revision 4da05a8edb55c6046cce958586c33b61da07bb79 --max-model-len 32768 --tensor-parallel-size 4 --gpu-memory-utilization 0.92 --host 0.0.0.0 --port 8000
