> @gromero PTAL, thanks!
argh! sorry, missed your previous ping long ago! So, just the nits in this
comment (https://github.com/apache/tvm-rfcs/pull/98#discussion_r1123874703) are
missing. Otherwise LGTM!
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs
+1
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/12743#issuecomment-1241311328
You are receiving this because you are subscribed to this thread.
Message ID:
@areusch @driazati @tqchen @tkonolige @manupak @Lunderberg @mbaret @junrushao
@Hzfengsy @slyubomirsky @ekalda thanks a lot for the reviews and support of
this RFC!
Tracking issue is created at: https://github.com/apache/tvm/issues/12690
Cheers.
--
Reply to this email directly or view it on G
OK, I agree @leandron @driazati Thanks.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/88#issuecomment-1218386487
You are receiving this because you are subscribed to this thread.
Message ID:
> @gromero I think I am getting a little confused at the difference between
> messages in the commits composing the PR and the final commit in main. To
> make things clearer, I think it would help to refer to to commit title and
> commit message as PR title and PR description, respectively. PR t
> Can you also include guidelines for 1. how the PR author can update their
> commits if they are not up to this standard (rebase?)
Let's say a PR has just been created. The idea is that regarding the commit
message (that will compose the final commit message) it doesn't matter the
commit(s) me
@areusch @leandron Could you please help me on how to trigger a [VOTE] thread
on this RFC? Cheers.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/88#issuecomment-1215261260
You are receiving this because you are subscribed to this thread.
Message I
@tqchen @jroesch @driazati @areusch @Mousius @manupak @tkonolige @mbaret
@leandron @alanmacd
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/88#issuecomment-1215257266
You are receiving this because you are subscribed to this thread.
Message ID:
This RFC proposes adding a Commmit Message Guideline to Apache TVM
documentation to help guide contributors on how to write good commit
messages when submitting code / Pull Requests.
Co-authored-by: Leandro Nunes
You can view, comment on, or merge this pull request online a
> > > @leandron, looking at Docker Hub (https://hub.docker.com/_/hello-world)
> > > it would appear the convention for image names is to use `-` there as
> > > well (i.e. `tlcpack/ci-cpu` rather than `tlcpack/ci_cpu`) can we go for
> > > that one?
> >
> >
> > Sure. I’ll push an updated version
@Mousius I don't have any further comments on it. Are you ok with the current
state of this RFC? If so, could you please approve the changes so I can merge
it? Thanks!
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/66#issuecomment-1148090614
You ar
Merged #76 into main.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/76#event-6757119416
You are receiving this because you are subscribed to this thread.
Message ID:
> cc @Mousius @gromero can you approve?
@leandron Hi. Are you still planing to change
https://github.com/apache/tvm-rfcs/pull/66#discussion_r854052265 ?
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/66#issuecomment-1125764615
You are receiving th
[quote="driazati, post:5, topic:12334, full:true"]
These guidelines are definitely good to have and I think we should codify them
in our docs! One big problem we have today is clicking the merge button on
GitHub defaults to a bad commit message which [[RFC] Allow merging via PR
comments](https
@tqchen Thanks a lot for input and support. I've changed the category as
pre-RFC and I'll add a few examples to the initial test. That's indeed
necessary I agree.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/commit-message-guideline/12334/7) to
respond.
You are receiving this beca
Hi Tristan. Good question ;)
In a sense that issue could be put into the class of the issues I mentioned as
"Github-specif issues", because to me ideally such a comments should never
exist in the first place. They exist in my understanding primarily because we
want to keep the PR conversation
@leandron Thanks a lot for the review.
--
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/43#issuecomment-964728491
@mehrdadh thanks for the review!
Yes, if a Project API method implementation is absent a `TypeError` will be
raised at the server side because the abstract method is not implemented when
the Handler class is derived. Also as per
https://github.com/apache/tvm-rfcs/blame/main/rfcs/0008-microtvm-p
RFC PR: https://github.com/apache/tvm-rfcs/pull/43
---
[Visit
Topic](https://discuss.tvm.apache.org/t/pre-rfc-tvmc-add-support-for-microtvm-targets/11221/22)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://
cc @areusch @mehrdadh @leandron @guberti
--
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/43#issuecomment-954271415
This RFC is about how TVMC (TVM CLI tool) can be extended to support microTVM
targets, considering the variety of platforms supported by microTVM, like Zephyr
and Arduino, and also considering future platforms, taking into account the use
of custom/adhoc platforms provided by users at their conveni
@areusch @mehrdadh Thanks for the initial reviews and inputs. I've fixed some
grammar in the text I found on the second read and incorporated your
suggestions.
I believe I can go ahead promoting that to a RFC by creating a PR at
https://github.com/apache/tvm-rfcs/ ?
---
[Visit
Topic](ht
> @gromero please take a look at the comments here and lmk when it's ready for
> another review
@areusch Hi. Please take a look. I've also added the text stressing that every
option must be associated at least to one API method, as per our discussion
last week in the Meetup. Thanks.
--
You ar
> I apologise for the wall of requested changes @gromero, I've been very nit
> picky over the clarity of the markdown which I think a find/replace will
> almost immediately fix the majority of.
>
> Overall this all sounds sensible and makes sense to me as a change.
@Mousius Actually, thanks a lo
Thanks a lot for the review @leandron
--
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/33#issuecomment-920051153
cc @areusch @manupa-arm
--
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/33#issuecomment-918581638
Hi, could the following RFC be reviewed please?
It is about extending the current metadata associated with project options
returned by the Project API.
Thank you.
Cheers,
Gustavo
You can view, comment on, or merge this pull request online at:
https://github.com/apache/tvm-rfcs/pull/33
-- Co
+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/8928#issuecomment-914211248
>> On generate_project method, and considering TVMC, my only comment is that it
>> should allow a project creation based also on MLF .tar, instead of only a
>> "live" executor.
>I agree; let's merge additional logic in project.py to do this as follow-on to
>this impl.
Sure! I'll submit a follow
> I agree we should support binary output. My thought is this would depend on
> the TVM target in use–but we can talk about it
Yeah I think so too. Like, I won't be good to always generated a .so and a .o
(for example) for the static runtime case, which afaics will only be
"interested" in the
> Great, let’s discuss Model Library Format a bit further on another RFC. I
> will try to start one early this week.
Cool. Thanks :)
>>> and a new command `tvmc micro gen-project` (or something) would be added to
>>> generate the e.g. Zephyr project.
>>
>>oh that’s cool. Copying (or generati
Hi Andrew!
Thanks a lot for the review.
> → First off, I agree with @manupa-arm and @leandron that we should split the
> compilation process into two pieces:
>
> 1. performing `tvm.relay.build` on a model (e.g. `tvmc compile`)
> 2. compiling a firmware binary (e.g. `tvmc micro build`)
> I thi
Hi Manupa,
> So the RPC feels like an optional layer above the runtime that calls into the
> runtime. When you have an fully fledged OS we can rely on dlopen to perform
> the necessary linking, thus it was not an issue in the non-micro TVM use
> cases.
> So for tvm micro use-cases that does
33 matches
Mail list logo