vllm的部署和使用

conda create -n cosyvoice python=3.10.9 cudnn=9.1.1.17 nvidia/label/cuda-12.1.1::cuda-toolkit ffmpeg x264

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

pip install vllm==0.6.6

pip install transformers==4.46 modelscope==1.20.1

qwen2.5模型下载

from modelscope import snapshot_download

Downloading model checkpoint to a local dir model_dir

model_dir = snapshot_download('Qwen/Qwen2.5-0.5B-Instruct')

model_dir = snapshot_download('Qwen/Qwen2.5-7B-Instruct')

model_dir = snapshot_download('Qwen/Qwen2.5-32B-Instruct')

model_dir = snapshot_download('Qwen/Qwen2.5-72B-Instruct')

model_dir = snapshot_download('Qwen/Qwen2.5-1.5B-Instruct')