$ vllm-t4 start
vllm-t4: swap already on: /opt1/swapfile (16777212 KB)
vllm-t4: Turing clamp confirmed
vllm-t4: starting google/gemma-4-E2B-it-qat-w4a16-ct on 127.0.0.1:8000
vllm-t4: pid 17215, log /home/xbill_glitnir_com/gemma4-dev/gpu-vllm-t4-2b/run/vllm.log
vllm-t4: waiting up to 1800s for http://127.0.0.1:8000/health
     0s  VRAM 0 MiB, 0 %
    75s  VRAM 0 MiB, 0 %
    90s  VRAM 1093 MiB, 10 %
   105s  VRAM 9005 MiB, 10 %
   166s  VRAM 9301 MiB, 0 %
   181s  VRAM 8403 MiB, 0 %
   241s  VRAM 13371 MiB, 0 %
   347s  VRAM 13371 MiB, 0 %
vllm-t4: healthy after 362s -- http://127.0.0.1:8000
✅ Serving at http://127.0.0.1:8000 (pid 17215).

VRAM 13371 MiB, 15360 MiB, 0 %