qwen.cpp icon indicating copy to clipboard operation
qwen.cpp copied to clipboard

💡 [Question] - QwenCPP Python Binding 如何 支持 BLAS CPU 加速

Open micronetboy opened this issue 2 years ago • 2 comments

起始日期 | Start Date

No response

实现PR | Implementation PR

No response

相关Issues | Reference Issues

No response

摘要 | Summary

QwenCPP Python Binding 如何 支持 BLAS CPU 加速

基本示例 | Basic Example

缺陷 | Drawbacks

未解决问题 | Unresolved questions

No response

micronetboy avatar Dec 15 '23 03:12 micronetboy

python binding 如何设置 OpenBLAS 在CPU上加速?谢谢

python binding 如何设置 cuBLAS 在GPU上加速?谢谢

micronetboy avatar Dec 15 '23 07:12 micronetboy

llama-cpp-python 有如下的选项,qwen-cpp 是否有类似的选项?

On Linux and Mac you set the CMAKE_ARGS like this:

CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python

micronetboy avatar Dec 15 '23 11:12 micronetboy