[GitHub] [tvm] tbaggu opened a new issue, #15448: OOM error when we export larger models

["tbaggu (via GitHub)" <gi...@apache.org>]

tbaggu opened a new issue, #15448:
URL: https://github.com/apache/tvm/issues/15448

   When we compile and export larger models like DLRM, after compilation.
   lib.export_library("model.so"), should save the module in .so but this process is being killed because OOM.
   
   I am working with DLRM 100GB model, with latest TVM on 500GB RAM 0 Swap memory on Linux.
   
   I am expecting  there should some chunk based export method ,since there are many larger models are coming on which we can't keep on increase RAM to just compile. 
   
   Is there any way to change the export method to support chunk based by limiting the RAM usage 
   


-- 
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.apache.org

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

Re: [I] OOM error when we export larger models [tvm]

["tqchen (via GitHub)" <gi...@apache.org>]

tqchen closed issue #15448: OOM error when we export larger models 
URL: https://github.com/apache/tvm/issues/15448


-- 
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