CUDA_DEVICE_ORDER=PCI_BUS_ID CUDA_VISIBLE_DEVICES=0,1,2,3 VLLM_NO_USAGE_STATS=1 DO_NOT_TRACK=1 vllm serve Qwen/Qwen3-8B-AWQ --revision 4da05a8edb55c6046cce958586c33b61da07bb79 --max-model-len 32768 --tensor-parallel-size 4 --gpu-memory-utilization 0.92 --host 127.0.0.1 --port 8000
