Thank you all for your replies.
[quote="tkonolige, post:2, topic:9893"]
It’s hard to figure out where to register the fixed inputs. For sparse its done
in the pass that converts dense matrices to sparse (which means you don’t get
fixed inputs if you model is already sparse).
[/quote]
Seems th
I would like to propose one thing that we need to consider whether this
platform have mobile apps or not; Another thing is whether this platform is
good to access from anywhere. For example, in China, it is not all platforms
can be accessed. :slight_smile:
---
[Visit
Topic](https://disc
According to the Apache Software Foundation ["Community Led Development: The
Apache Way"](https://www.apache.org/foundation/how-it-works.html#communication)
guidelines, there are several options available for communication amongst a
community:
> Communication is via mailing lists. These are "
Out of curiosity. What is the status for the RFC/PR?
Thanks!
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-byoc-android-nnapi-integration/9072/8)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://di
+1
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833986813
As per discussion, I will prepare the PR to change the API to `numpy` and add a
deprecation warning message in the `asnumpy`.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-api-change-asnumpy-numpy/9846/9) to
respond.
You are receiving this because you enabled mailing list mode.
+1
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833926694
The main issue with the previous approach is that it wasn't possible to
transform the reference input when a schedule needed layout transformations.
I'm okay with bringing something back so long as we have a way to either
1. handle layout transformations to `ref_input`
2. determine when layout
+1
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833818722
> @Lunderberg @junrushao1994 good catch, would changing "abandoned" to
> "postponed" resolve the ambiguity sufficiently?
Thank you! That resolves my question.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.
+1
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833770287
+1 Thanks @hogepodge for your hard work on this!
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833766117
Thanks @hogepodge! Yeah that sounds better to me
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833755970
@Lunderberg @junrushao1994 good catch, would changing "abandoned" to
"postponed" resolve the ambiguity sufficiently?
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-8337
Right now we allow adding attributes of operators in python:
https://github.com/apache/tvm/blob/main/src/ir/op.cc#L105.
I suspect that we don't have a public API to add operators on the python side
right now, and I don't know the reason why not. If you wanted to, you may just
expose `OpRegEnt
+1
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833728641
+1
Agree with @Lunderberg on the tracking issue
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833725537
+1
One small question: Under "Tracking Issue", the tracking issue is closed "when
the RFC is either completed or abandoned." Is "abandoned" the same as
"postponed" in this context, or is there a distinction between them?
--
You are receiving this because you are subscribed to this thread.
Rep
Thanks for everyone's discussion. Please participating the vote here
https://github.com/apache/tvm/issues/7991 to formally adopt the RFC process
---
[Visit Topic](https://discuss.tvm.apache.org/t/rfc-update-rfc-process/9033/14)
to respond.
You are receiving this because you enabled mailin
+1
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833699197
+1
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7991#issuecomment-833698474
Dear Community:
This is a formal vote to adopt the new RFC process after being discussed in the
community for a while. Please see the proposed process here
https://github.com/apache/tvm-rfcs
This is a formal voting thread for the community to adopt the new RFC process.
Please vote
Vote:
+1
Merged #2 into main.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/2#event-4696543141
23 matches
Mail list logo
