This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new c36ae1cb3a [Arith][UnitTest] Parametrize tests of
masahi merged PR #13923:
URL: https://github.com/apache/tvm/pull/13923
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail:
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 5456fae776 [TVMScript,Fix] Fix findsource when classes are indented
(#13924)
add 282f17584b [Arith] Updated
tvm-bot commented on PR #13930:
URL: https://github.com/apache/tvm/pull/13930#issuecomment-1421807852
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews
vinx13 opened a new pull request, #13930:
URL: https://github.com/apache/tvm/pull/13930
This changes `index_map` argument of `TransformLayout` from attr to input.
It allows the index map to capture the random variables in the environment.
This will allow tuning with different `index_map`
tvm-bot commented on PR #13929:
URL: https://github.com/apache/tvm/pull/13929#issuecomment-1421681306
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews
tvm-bot commented on PR #13929:
URL: https://github.com/apache/tvm/pull/13929#issuecomment-1421681324
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews
tvm-bot commented on PR #13929:
URL: https://github.com/apache/tvm/pull/13929#issuecomment-1421681320
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews
dependabot[bot] opened a new pull request, #13929:
URL: https://github.com/apache/tvm/pull/13929
Bumps [cryptography](https://github.com/pyca/cryptography) from 37.0.2 to
39.0.1.
Changelog
Sourced from https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst;>cryptography's
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch
dependabot/pip/docker/python/cryptography-39.0.1
in repository https://gitbox.apache.org/repos/asf/tvm.git
at ceda1a6da5 Bump cryptography from 37.0.2 to 39.0.1 in /docker/python
No
junrushao commented on PR #13928:
URL: https://github.com/apache/tvm/pull/13928#issuecomment-1421678495
Will add a regression test over the weekend
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go
junrushao commented on PR #13928:
URL: https://github.com/apache/tvm/pull/13928#issuecomment-1421676223
CC: @Icemist @echuraev @masahi
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the
tvm-bot commented on PR #13928:
URL: https://github.com/apache/tvm/pull/13928#issuecomment-1421674335
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews
junrushao opened a new pull request, #13928:
URL: https://github.com/apache/tvm/pull/13928
This typo was introduced a while ago, but was not uncovered until I was
rebasing Relax when a unittest crashes.
--
This is an automated message from the Apache Git Service.
To respond to the
This is an automated email from the ASF dual-hosted git repository.
driazati pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 6fb961a945 [CI] Include static builds of the runtime
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a commit to branch junrushao-patch-1
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 7b52b4a8d5e379ae34141d28cdb45d2be1054328
Author: Junru Shao
AuthorDate: Tue Feb 7 16:05:18 2023 -0800
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a change to branch junrushao-patch-1
in repository https://gitbox.apache.org/repos/asf/tvm.git
at 7b52b4a8d5 [MetaSchedule] Fix a typo in MemoryDatabase
This branch includes the following new commits:
driazati merged PR #13612:
URL: https://github.com/apache/tvm/pull/13612
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail:
guberti commented on code in PR #13815:
URL: https://github.com/apache/tvm/pull/13815#discussion_r1099312483
##
python/tvm/topi/arm_cpu/mprofile/dsp/micro_kernel/multi_channel_convolve.py:
##
@@ -179,20 +179,26 @@ def _dual_int16_channel_convolve_impl(_tensor_h,
tensor_w,
mehrdadh commented on PR #13612:
URL: https://github.com/apache/tvm/pull/13612#issuecomment-1421505002
Thanks @gigiblender, LGTM!
cc @driazati for review as well
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
gigiblender commented on PR #13612:
URL: https://github.com/apache/tvm/pull/13612#issuecomment-1421493250
> @gigiblender I think this PR needs to be rebased
@mehrdadh ready for review
--
This is an automated message from the Apache Git Service.
To respond to the message, please log
junrushao commented on PR #13925:
URL: https://github.com/apache/tvm/pull/13925#issuecomment-1421490590
That makes sense! Thanks for updating it!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to
mehrdadh commented on code in PR #13885:
URL: https://github.com/apache/tvm/pull/13885#discussion_r1099250461
##
apps/microtvm/zephyr/template_project/microtvm_api_server.py:
##
@@ -413,6 +419,9 @@ def _create_prj_conf(
"CONFIG_UART_INTERRUPT_DRIVEN=y\n"
Lunderberg commented on PR #13918:
URL: https://github.com/apache/tvm/pull/13918#issuecomment-1421466220
The changes look reasonable, and thank you on the catch. The check was
intended to identify cases where there is a known lower bound (i.e. not
`kNegInf`) less than zero. This didn't
areusch commented on issue #12651:
URL: https://github.com/apache/tvm/issues/12651#issuecomment-1421278930
0
Ultimately I'd prefer to get more clarity on this direction, but given we
are getting that through the new `unity` branch, it makes sense to adopt this
proposal as the "goal"
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from c8b99a93a1 Fix build platform environment variable (#13914)
add 7149142781 [TVMScript] Schedule error reporting with
tqchen merged PR #13921:
URL: https://github.com/apache/tvm/pull/13921
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail:
areusch commented on code in PR #13885:
URL: https://github.com/apache/tvm/pull/13885#discussion_r1099030975
##
apps/microtvm/arduino/template_project/src/example_project/project.ino:
##
@@ -17,10 +17,10 @@
* under the License.
*/
-#include "src/model.h"
+#include
mbaret commented on issue #12651:
URL: https://github.com/apache/tvm/issues/12651#issuecomment-1421236617
+1
I'd love for us to have more clarity on the future of Relax and Relay, but I
don't think vetoing this proposal is now progressing that goal any further.
Instead, we're seeing
tkonolige commented on PR #13925:
URL: https://github.com/apache/tvm/pull/13925#issuecomment-1421158781
How about if I move these functions to `python/tvm/target/x86.py`?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
FranklandJack commented on code in PR #13920:
URL: https://github.com/apache/tvm/pull/13920#discussion_r1098942435
##
src/relay/backend/contrib/cmsisnn/relay_to_tir.cc:
##
@@ -587,10 +587,11 @@ class RelayToTIRVisitor : public MixedModeMutator {
}
void EmitMul(const
tqchen commented on PR #13916:
URL: https://github.com/apache/tvm/pull/13916#issuecomment-1421046938
Thanks, @Mousius as I clarified, the branch development in `unity` offers
some flexibility to help us through the branch establishment stage.
The reality is that we want to do more
tqchen commented on PR #13926:
URL: https://github.com/apache/tvm/pull/13926#issuecomment-1420987354
First of all, it is important indeed important to group things into
reasonably isolated components that have reasonable structure.
That does not mean, however, that such logical
arina-grovety commented on code in PR #13212:
URL: https://github.com/apache/tvm/pull/13212#discussion_r1098760968
##
python/tvm/relay/frontend/common.py:
##
@@ -1067,6 +1067,20 @@ def __init__(self, span):
self._span =
Mousius commented on PR #13916:
URL: https://github.com/apache/tvm/pull/13916#issuecomment-1420894409
> The idea is that even though things may not have been caught immediately
by one of us(such as test coverage), having a quick followup comment such as
(please add test coverage) will
Mousius commented on PR #13926:
URL: https://github.com/apache/tvm/pull/13926#issuecomment-1420894510
> Coming back to the branch establishment stage. It is indeed hard for
community members who are not yet in the related code areas to be able to
digest under the context of a single
padreofthegame opened a new pull request, #13927:
URL: https://github.com/apache/tvm/pull/13927
…of input tensors
This PR should enable full functionality of matmul operator in PyTorch
frontend. In addition to current behavior, it introduces:
- matrix multiplication of two 1D
tvm-bot commented on PR #13927:
URL: https://github.com/apache/tvm/pull/13927#issuecomment-1420886920
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews
Lunderberg commented on PR #13922:
URL: https://github.com/apache/tvm/pull/13922#issuecomment-1420856222
> Hi :) , is it a typo for x > 0? @Lunderberg
Thank you, and yes, that was a typo. The condition was updated to require
`x > 0`.
--
This is an automated message from the
tqchen commented on PR #13926:
URL: https://github.com/apache/tvm/pull/13926#issuecomment-1420744226
We have not yet decided on how `unity` will get merged into main. Likely the
community will need to look at the unity branch as a whole to get enough
context for merging into the main. It
tqchen commented on PR #13916:
URL: https://github.com/apache/tvm/pull/13916#issuecomment-1420682896
I would like to followup and say that when we experiment different modes of
operations at different period of the development. My take is that we will gain
more parallelism after the branch
tqchen commented on PR #13916:
URL: https://github.com/apache/tvm/pull/13916#issuecomment-1420654749
Thanks @Mousius, thank you for your inputs .
Agree that it is a challenge to be able to get ramped up and look into the
set of changes just in a PR. The good part of branch
gromero commented on PR #13926:
URL: https://github.com/apache/tvm/pull/13926#issuecomment-1420631047
@junrushao Is the idea that these PRs (like this one) being merged into
`unity` branch will get at some point in the future be merged into `main`
branch as-is?
--
This is an automated
Mousius commented on PR #13916:
URL: https://github.com/apache/tvm/pull/13916#issuecomment-1420611019
Hi @tqchen,
> In order to get unity merged into main, we will need to ensure the end
state (at the merging proposal) of the unity branch gets to a ready state.
Merging large
ashutosh-arm commented on code in PR #13918:
URL: https://github.com/apache/tvm/pull/13918#discussion_r1098522045
##
src/tir/transforms/lower_intrin.cc:
##
@@ -214,8 +221,15 @@ class IntrinInjecter : public
tvm::arith::IRMutatorWithAnalyzer {
// If the numerator's lower
ashutosh-arm commented on code in PR #13918:
URL: https://github.com/apache/tvm/pull/13918#discussion_r1098522045
##
src/tir/transforms/lower_intrin.cc:
##
@@ -214,8 +221,15 @@ class IntrinInjecter : public
tvm::arith::IRMutatorWithAnalyzer {
// If the numerator's lower
wangzy0327 commented on PR #13847:
URL: https://github.com/apache/tvm/pull/13847#issuecomment-1420550063
@ masahi @mvermeulen I use the commit masahi:rocm-t-fix to build and run
code.But I get error as follow.
onnx_rocm.py
```
from pyexpat import model
import onnx
Liam-Sturge commented on issue #13871:
URL: https://github.com/apache/tvm/issues/13871#issuecomment-1420458484
Issue was resolved by PR https://github.com/Maratyszcza/NNPACK/pull/214.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to
This is an automated email from the ASF dual-hosted git repository.
ashutoshp pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 7323e1d16f [OpenCL] Refactor OpenCL init function (#13919)
add c8b99a93a1 Fix build platform environment variable
Liam-Sturge closed issue #13871: [CI Problem] Docker install NNPACK fails to
build
URL: https://github.com/apache/tvm/issues/13871
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific
ashutosh-arm merged PR #13914:
URL: https://github.com/apache/tvm/pull/13914
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail:
51 matches
Mail list logo