Zhengyan Zhang
Results
2
comments of
Zhengyan Zhang
> 是不是推理的时候,bminf将线程层转换成量化线性层,最终实现参数从fp16到int8,然后bminf计算也是int8 是的,保存的精度没有变化,需要再面向bminf转换一下。
Thank you for your feedback. We have addressed this issue with a fix. Please try updating to the latest version, and let us know if you encounter any further problems.