You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2019/11/27 00:47:54 UTC

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4406: [RFC] Apache TVM 0.6.0 Release Candidate (verifying, feedback, etc.)

tqchen edited a comment on issue #4406: [RFC] Apache TVM 0.6.0 Release Candidate (verifying, feedback, etc.)
URL: https://github.com/apache/incubator-tvm/issues/4406#issuecomment-558878894
 
 
   reported by @tmoreau89 and @liangfu There is a broken tutorial  https://github.com/apache/incubator-tvm/blob/master/vta/tutorials/frontend/deploy_vision_on_vta.py  which was caused by quantization changes that need to be fixed.
   
   Originally the quantize pass won't produce multiply if the scale is power2, and it is a hard requirement for VTA because vta does not have multiplier. seems the change https://github.com/apache/incubator-tvm/pull/4295 allows creation of model with mul. @vinx13 would be great if you can help look into the problem.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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