manupa-arm edited a comment on pull request #9: URL: https://github.com/apache/tvm-rfcs/pull/9#issuecomment-875094037
Thanks @tkonolige for taking a look at this. As per the pre-RFC discussion, There is not anything preventing us from integrating unified static memory planner (apart from doing actual work for that of course :) ) for graph executor as long as relay "main" function is lowered to TIR before creating the JSON (or maybe not create the json at all -- see the discuss post conversation). Thus, the design does not block such integration. For VM, Im not sure how useful "static" memory planning would be. Drawbacks -- The relay "main" function has to be lowered to TIR to use the USMP. (I ll add a section) -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
