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

Posted to commits@tvm.apache.org by "tqchen (via GitHub)" <gi...@apache.org> on 2023/01/31 23:00:03 UTC

[GitHub] [tvm] tqchen commented on pull request #13877: [VM][DMLC] Lower memory usage when loading and dumping weights

tqchen commented on PR #13877:
URL: https://github.com/apache/tvm/pull/13877#issuecomment-1411185588

   The approach of having overload file support util is fine, one thing is that it would needs to be part of the runtime folder as it is simple enough. 
   
   Given most of the cases are on GPU, having ability to be able to load one array into CPU, copy into GPU then immediately free that CPU array can also be effective.


-- 
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.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org