@jdavies-huawei Agree it would be better to have a section dedicated to
threads. I just posted an issue/bug to the github
https://github.com/dmlc/tvm/issues/3052, resolving which shall help developers
understand the concept of threads better.
---
[Visit
Topic](https://discuss.tvm.ai/t/di
Closed #2994.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/2994#event-2288781186
Another immature idea is to unify composite types with operator's attributes
(but maybe far long-term)
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/3042#issuecomment-484789903
This is a great progress towards deploying real-world NLP models. Thanks Jared
for proposing this!
As far as I could tell, however, in the long term, we probably need more
support for more general dependent typing for more data types. I am afraid that
we will have to consider composite types in
