Thanks for this great job !
Based on our experience at Meituan, dynamic shape is important for our use
cases, e.g. OCR and ASR models with dynamic seq_len. Now we could solve these
with relax and vm runtime :)
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-r
Issue Tracking RFC - https://github.com/apache/tvm/issues/12801
cc: @areusch
You can view, comment on, or merge this pull request online at:
https://github.com/apache/tvm/pull/12988
-- Commit Summary --
* [skip ci] Added links to label tag wiki page in issue templates to align
with Issue
In Intellif, people build, maintain and extend the DL compilation stack with
Relay in past years. However, we never think the upstreaming of a new module
would break existing functionalities or cause confusions, but huge
opportunities to solve many technical issues which prove to be not so easy
