Hannes von Essen

docker run --rm -it \
  --network host \
  --shm-size=8g \
  --ulimit memlock=-1 \
  --ulimit stack=67108864 \
  --runtime=nvidia \
  --name=vllm-serve \
  -e HF_TOKEN=hf_*** \
  -e HF_HOME=/root/.cache/huggingface \
  ghcr.io/nvidia-ai-iot/vllm:latest-jetson-orin \
  vllm serve "embedl/Cosmos-Reason2-2B-W4A16-Edge2" \
    --max-model-len 8192 \
    --gpu-memory-utilization 0.75 \
    --max-num-seqs 2

docker run --rm -it \
  --network host \
  --shm-size=8g \
  --ulimit memlock=-1 \
  --ulimit stack=67108864 \
  --runtime=nvidia \
  --name=vllm-serve \
  -e HF_TOKEN=hf_*** \
  -e HF_HOME=/root/.cache/huggingface \
  nvcr.io/nvidia/vllm:26.01-py3 \
  vllm serve "embedl/Cosmos-Reason2-2B-NVFP4A16" \
    --host 0.0.0.0 \
    --port 8000 \
    --tensor-parallel-size 1 \
    --max-model-len 16384 \
    --gpu-memory-utilization 0.9