sudo docker run -d \
  --name qwen-14b-vllm \
  --restart unless-stopped \
  --runtime nvidia \
  --gpus all \
  --ipc=host \
  -p 8001:8000 \
  -v /home/azurian/.cache/huggingface:/root/.cache/huggingface \
  -e HF_TOKEN="$HF_TOKEN" \
  vllm/vllm-openai:latest \
  --model Qwen/Qwen2.5-14B-Instruct \
  --served-model-name Qwen/Qwen2.5-14B-Instruct \
  --host 0.0.0.0 \
  --port 8000