win10 cpu 下使用Xinference来进行大模型的推理测试

创建环境
conda remove --name xinference --all
conda create --name xinference python=3.10
conda activate xinference

#仅cpu
pip install xinference --force -i https://pypi.tuna.tsinghua.edu.cn/simple #
pip install “xinference[transformers]” -i https://pypi.tuna.tsinghua.edu.cn/simple
xinference-local
#下载
#https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.55/llama_cpp_python-0.2.55-cp310-cp310-win_amd64.whl
#pip install D:\cuda\llama_cpp_python-0.2.55-cp310-cp310-win_amd64.whl

#https://github.com/li-plus/chatglm.cpp/releases/download/v0.3.1/chatglm_cpp-0.3.1-cp310-cp310-win_amd64.whl
#pip install D:\cuda\chatglm_cpp-0.3.1-cp310-cp310-win_amd64.whl

#pip install “xinference[all]” -i https://pypi.tuna.tsinghua.edu.cn/simple #仅能用于linux
#pip install “xinference[vllm]” -i https://pypi.tuna.tsinghua.edu.cn/simple #仅能用于linux
#pip install ‘xinference[sglang]’ -i https://pypi.tuna.tsinghua.edu.cn/simple #仅能用于linux