python -c "import torch; print('PyTorch:', torch.__version__); print('ROCm available:', torch.cuda.is_available()); print('Device:', torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'N/A')"

pip config set global.index-url https://mirrors.cloud.tencent.com/pypi/simple/

pip install modelscope

modelscope download --model google/gemma-4-E4B-it --cache_dir "./models"

ls -lh ./models/google/gemma-4-E4B-it/

uv pip uninstall --system torchvision torchaudio

uv pip install --system 'vllm==0.23.0+rocm723' torchvision torchaudio 'fastapi[standard]==0.136.0' \
  --no-cache \
  --index-url https://mirrors.aliyun.com/pypi/simple/ \
  --extra-index-url https://wheels.vllm.ai/rocm/ \
  -U

vllm serve ./models/google/gemma-4-E4B-it/ --served-model-name gemma-4-E4B-it

vllm chat --url http://localhost:8000/v1 --model gemma-4-E4B-it