You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2018/12/22 10:48:17 UTC

[GitHub] kice opened a new issue #13720: Huge performance decrease by quantization

kice opened a new issue #13720: Huge performance decrease by quantization
URL: https://github.com/apache/incubator-mxnet/issues/13720
 
 
   I use the code from PR https://github.com/apache/incubator-mxnet/pull/13715, and I got a huge performance decrease by doing quantization on my model. I tested on Windows 10 with CUDA 10 and cudnn7 on Titan X (Pascal), using pre-release build from pip mxnet-cu100.
   
   Alought by this issue https://github.com/apache/incubator-mxnet/issues/10897, it claimed that INT8 quantization can save GPU memory during usage, I got almose **2x more** VRAM usage by quantization.
   
   Do we excepted that INT8 quantization is super slow and use more memory on GPU?
   
   And I may assume that UINT8 quantization is not yet supported since the UINT8 quantizated parameters is signed integer.
   
   So, do we have any plan for improving INT8 quantization in the near future?

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services