Awesome! Thanks so much for the update. @jroesch sorry to bug you while you're
working on your thesis, I'll bug @mbrookhart if I have any questions :)
---
[Visit
Topic](https://discuss.tvm.ai/t/rfc-relay-program-matching-for-relay-pt-1-a-pattern-language/5833/23)
to respond.
You are rece
@jroesch, is there any update on this feature? I'm really excited to try it out
:)
---
[Visit
Topic](https://discuss.tvm.ai/t/rfc-relay-program-matching-for-relay-pt-1-a-pattern-language/5833/20)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe fr
Got it. Would you mind sharing some details about the implementation? Or the
branch you’re currently working on?
I’m working on a feature that will be the opposite of what you’re doing:
creating a TF runtime module that will be invoked by the TVM runtime. The RFC
is
[here](http://tracking.di
**Problem**
In order for TVM to work as a generic compiler for frontend frameworks, it
needs to support all of the operators that those frontend frameworks support.
Relay already supports many operators for numerous frontends, and this operator
list tends to be sufficient for a handful of use
This is usually defined in Python. So for example, if you define your op’s call
to `_make` in `python/tvm/relay/op/tensor.py`, the schedule and op pattern are
usually defined in `python/tvm/relay/op/_tensor.py`
There are lots of examples in the `_*.py` files.
---
[Visit
Topic](https://di
