Llama-3.2-1B-Instruct (Ascend NPU)

# 基础环境 (CANN 8.5.1 + torch_npu 2.9.0 需预先安装)
pip install vllm vllm-ascend

# 验证 NPU 可用
npu-smi info
python -c "import torch; import torch_npu; print(torch.npu.device_count())"

# 从 HuggingFace 下载
pip install huggingface_hub
huggingface-cli download meta-llama/Llama-3.2-1B-Instruct \
  --local-dir ./LLM-Research/Llama-3.2-1B-Instruct

# 或从 ModelScope 下载
pip install modelscope
python -c "from modelscope import snapshot_download; \
  snapshot_download('LLM-Research/Llama-3.2-1B-Instruct', cache_dir='.')"

vllm serve ./LLM-Research/Llama-3.2-1B-Instruct \
  --dtype bfloat16 \
  --tensor-parallel-size 1 \
  --max-model-len 131072 \
  --port 8000

curl http://127.0.0.1:8000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "./LLM-Research/Llama-3.2-1B-Instruct",
    "messages": [{"role": "user", "content": "Hello, how are you?"}],
    "temperature": 0,
    "max_tokens": 128
  }'

{
  "choices": [{
    "message": {
      "content": "Hello! I'm just a computer program, so I don't have feelings, but I'm functioning properly and ready to help you with any questions or tasks you have. How can I assist you today?"
    }
  }],
  "usage": {"prompt_tokens": 37, "completion_tokens": 32, "total_tokens": 69}
}

python inference.py --prompt "What is the capital of France?"
# Output: The capital of France is Paris.

python inference.py --interactive  # 交互对话模式
python inference.py --health        # 健康检查