This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from e7e29b450b [ci] Fix build android rpc failure (#12216)
add 2b3e1eb3f5 [ci] Reinstall junintparser
github-actions[bot] commented on PR #12178:
URL: https://github.com/apache/tvm/pull/12178#issuecomment-1200051456
Built docs for commit ea3c93e5c890a4545e1648c9a0f9e47936324ade can be found
[here](https://pr-docs.tlcpack.ai/PR-12178/5/docs/index.html).
--
This is an automated
github-actions[bot] commented on PR #12221:
URL: https://github.com/apache/tvm/pull/12221#issuecomment-1200050594
Built docs for commit 07362baebc89135f5613517bd6bba494e844c290 can be found
[here](https://pr-docs.tlcpack.ai/PR-12221/15/docs/index.html).
--
This is an automated
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from cfefa90a96 [Adreno] Update conv2d_nhwc test to use winograd (#12214)
add 195e60b97a [FIX,ROOFLINE]
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 db4380cf41 [ci][docker] create Dockerfile.ci_riscv
driazati merged PR #12230:
URL: https://github.com/apache/tvm/pull/12230
--
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-docker-update
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard e5c7e22e03 [ci][docker] Nightly Docker image update
add 9a4d80c5fe Removing header arm_math.h
yongwww opened a new issue, #12238:
URL: https://github.com/apache/tvm/issues/12238
These tests were found to be flaky (intermittently failing on `main` or
failed in a PR with unrelated changes). See [the
yongwww commented on issue #11462:
URL: https://github.com/apache/tvm/issues/11462#issuecomment-1200029812
Summary for 7/25/22 - 7/29/22:
[jenkins](https://ci.tlcpack.ai/blue/organizations/jenkins/tvm/detail/main/3900/pipeline/)
on
mehrdadh commented on code in PR #12207:
URL: https://github.com/apache/tvm/pull/12207#discussion_r933629167
##
python/tvm/micro/testing/evaluation.py:
##
@@ -153,4 +163,4 @@ def evaluate_model_accuracy(session, aot_executor,
input_data, true_labels, runs
num_correct =
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 2b3e1eb3f5 [ci] Reinstall junintparser after zephyr
driazati merged PR #12226:
URL: https://github.com/apache/tvm/pull/12226
--
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:
driazati closed issue #11749: [ci] pytest_wrapper needs guards for invalid
JUnits
URL: https://github.com/apache/tvm/issues/11749
--
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
driazati commented on PR #12226:
URL: https://github.com/apache/tvm/pull/12226#issuecomment-1199961871
No it doesn't, we'll have to merge and try an update
--
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
ArmageddonKnight commented on PR #11793:
URL: https://github.com/apache/tvm/pull/11793#issuecomment-1199910934
@renfeier The reason is ebcause we are refactoring the implementation, so
the pass itself is temporarily commented out. Sorry I was quite busy with
university business and will
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 e7e29b450b [ci] Fix build android rpc failure
driazati merged PR #12216:
URL: https://github.com/apache/tvm/pull/12216
--
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 PR #12189:
URL: https://github.com/apache/tvm/pull/12189#issuecomment-1199899208
In retrospect, I should have written a new message that tagged all the
previous reviewers, as well as re-requesting reviews with the GitHub API for
that. It would be awesome to have that
guberti commented on code in PR #12207:
URL: https://github.com/apache/tvm/pull/12207#discussion_r933564689
##
python/tvm/micro/testing/pytest_plugin.py:
##
@@ -0,0 +1,126 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license
yelite opened a new pull request, #12237:
URL: https://github.com/apache/tvm/pull/12237
This PR:
- Adds the registry of printing function (traced_object_layered_functor.cc)
Compared to the prototype version, this:
- Consolidates the implementation into a single class, since
mbrookhart opened a new pull request, #12236:
URL: https://github.com/apache/tvm/pull/12236
I have no idea what I was thinking when I wrote that function
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
This is an automated email from the ASF dual-hosted git repository.
kparzysz 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 c6d733a7eb [TOPI][HEXAGON] Implement depthwise
kparzysz-quic merged PR #12218:
URL: https://github.com/apache/tvm/pull/12218
--
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:
tkonolige commented on PR #79:
URL: https://github.com/apache/tvm-rfcs/pull/79#issuecomment-1199837603
I'm still a bit confused on 2. The example you give for a single class is
one that has all static members, but what if instead it was just a regular
class. It would instantiate a single
mehrdadh opened a new issue, #12235:
URL: https://github.com/apache/tvm/issues/12235
we had multiple instances where code changes resulted in skipping tests in
the CI unintentionally. It would be great if we can have a tool which keeps
track of the tests. Here are some instances:
-
vinx13 commented on issue #12199:
URL: https://github.com/apache/tvm/issues/12199#issuecomment-1199819899
cc @zxybazh
--
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
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from d183a4f306 [microTVM][Zephyr][projectAPI] Minimize project build
commands (#12209)
add d19570fb23 [UX] highlight
junrushao1994 merged PR #12197:
URL: https://github.com/apache/tvm/pull/12197
--
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:
TejashShah commented on issue #9685:
URL: https://github.com/apache/tvm/issues/9685#issuecomment-1199709337
cc @mehrdadh Is this issue addressed or do we need to follow up on this?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to
yelite commented on code in PR #12232:
URL: https://github.com/apache/tvm/pull/12232#discussion_r933396360
##
src/contrib/torch/tvm_module_wrapper/runtime_bridge.h:
##
@@ -0,0 +1,53 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor
tkonolige commented on code in PR #12205:
URL: https://github.com/apache/tvm/pull/12205#discussion_r933410603
##
tests/python/unittest/test_roofline.py:
##
@@ -0,0 +1,121 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.
tkonolige commented on code in PR #12205:
URL: https://github.com/apache/tvm/pull/12205#discussion_r933410021
##
python/tvm/utils/roofline/cuda.py:
##
@@ -0,0 +1,232 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See
yelite commented on code in PR #12232:
URL: https://github.com/apache/tvm/pull/12232#discussion_r933381946
##
cmake/modules/contrib/PT_TVMDSOOP.cmake:
##
@@ -21,38 +21,55 @@ if(NOT USE_PT_TVMDSOOP STREQUAL "OFF")
execute_process(COMMAND ${PYTHON_EXECUTABLE} -c "import torch;
gigiblender commented on code in PR #12178:
URL: https://github.com/apache/tvm/pull/12178#discussion_r933383395
##
tests/scripts/task_cpp_unittest.sh:
##
@@ -45,20 +45,23 @@ python3 tests/scripts/task_build.py \
--cmake-target cpptest \
--build-dir "${BUILD_DIR}"
-#
yelite commented on code in PR #12232:
URL: https://github.com/apache/tvm/pull/12232#discussion_r933381946
##
cmake/modules/contrib/PT_TVMDSOOP.cmake:
##
@@ -21,38 +21,55 @@ if(NOT USE_PT_TVMDSOOP STREQUAL "OFF")
execute_process(COMMAND ${PYTHON_EXECUTABLE} -c "import torch;
paperplanet opened a new pull request, #12234:
URL: https://github.com/apache/tvm/pull/12234
Currently, lowering qnn.requantize in FP mode generates duplictated cast to
float ops at the beginning, this patch removes the dpulicated cast op.
cc @masahi @AndrewZhaoLuo for code review.
kparzysz-quic commented on PR #12140:
URL: https://github.com/apache/tvm/pull/12140#issuecomment-1199378156
Pinging all interested parties... Are there any concerns that haven't been
addressed?
--
This is an automated message from the Apache Git Service.
To respond to the message,
This is an automated email from the ASF dual-hosted git repository.
mehrdadh pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from aeda760e5e [TIR] Disallow unused rhs vars in GetAutoTensorizeMapping
(#12225)
add d183a4f306
mehrdadh merged PR #12209:
URL: https://github.com/apache/tvm/pull/12209
--
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:
tmoreau89 commented on PR #12231:
URL: https://github.com/apache/tvm/pull/12231#issuecomment-1199322956
CC @vanessahlyan 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
URL above to go to the specific
ashutosh-arm commented on code in PR #12215:
URL: https://github.com/apache/tvm/pull/12215#discussion_r933262523
##
src/relay/transforms/remove_standalone_reshapes.cc:
##
@@ -0,0 +1,122 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
tmoreau89 commented on PR #12231:
URL: https://github.com/apache/tvm/pull/12231#issuecomment-1199275968
CC @adelbertc for now
--
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
zhang-yi-chi closed pull request #12229: [Relay][Frontend][Onnx] Add GridSample
operator for ONNX frontend
URL: https://github.com/apache/tvm/pull/12229
--
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
zhang-yi-chi commented on PR #12229:
URL: https://github.com/apache/tvm/pull/12229#issuecomment-1199232763
should wait until onnxruntime is upgraded to 1.11.0 with opset 16.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
zhang-yi-chi closed issue #12233: [Flaky Test]
`tests/python/frontend/onnx/test_forward.py::test_grid_sample[llvm]`
URL: https://github.com/apache/tvm/issues/12233
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
zhang-yi-chi opened a new issue, #12233:
URL: https://github.com/apache/tvm/issues/12233
Related pull requests #12229
These tests were found to be flaky (intermittently failing on `main` or
failed in a PR with unrelated changes). See [the
blackkker commented on code in PR #12028:
URL: https://github.com/apache/tvm/pull/12028#discussion_r933048302
##
tests/python/frontend/tensorflow/test_forward.py:
##
@@ -498,7 +501,7 @@ def _test_convolution(
add_shapes_to_graph_def=True,
):
"""One iteration of
SebastianBoblest commented on code in PR #12028:
URL: https://github.com/apache/tvm/pull/12028#discussion_r933045267
##
tests/python/frontend/tensorflow/test_forward.py:
##
@@ -498,7 +501,7 @@ def _test_convolution(
add_shapes_to_graph_def=True,
):
"""One iteration
SebastianBoblest commented on code in PR #12028:
URL: https://github.com/apache/tvm/pull/12028#discussion_r933045267
##
tests/python/frontend/tensorflow/test_forward.py:
##
@@ -498,7 +501,7 @@ def _test_convolution(
add_shapes_to_graph_def=True,
):
"""One iteration
blackkker commented on code in PR #12028:
URL: https://github.com/apache/tvm/pull/12028#discussion_r933037538
##
tests/python/frontend/tensorflow/test_forward.py:
##
@@ -498,7 +501,7 @@ def _test_convolution(
add_shapes_to_graph_def=True,
):
"""One iteration of
juda commented on code in PR #12232:
URL: https://github.com/apache/tvm/pull/12232#discussion_r933036589
##
cmake/modules/contrib/PT_TVMDSOOP.cmake:
##
@@ -21,38 +21,55 @@ if(NOT USE_PT_TVMDSOOP STREQUAL "OFF")
execute_process(COMMAND ${PYTHON_EXECUTABLE} -c "import torch;
juda opened a new pull request, #12232:
URL: https://github.com/apache/tvm/pull/12232
This PR solves two issues:
1. The compatibility of libstdc++ CXX11 ABI.
Currently, the official PyTorch distribution uses old symbols from
libstdc++, which conflicts with the symbols used by
vvchernov commented on PR #12231:
URL: https://github.com/apache/tvm/pull/12231#issuecomment-1199023066
Hello @tmoreau89! Could you see this PR and please tag Adalbert and Vanessa,
I do not know their nicknames in github
--
This is an automated message from the Apache Git Service.
To
vvchernov opened a new pull request, #12231:
URL: https://github.com/apache/tvm/pull/12231
The main idea is to construct some handshake mechanism which can help to
check that TVM executor obtained from pre-compiled libraries and other files is
corresponded to given model.
There is a
alter-xp commented on issue #11688:
URL: https://github.com/apache/tvm/issues/11688#issuecomment-1198994195
hi @areusch, I created a [Dockerfile.ci_riscv
(pr)](https://github.com/apache/tvm/pull/12230), which only retains the basic
environment and riscv related content in
junrushao1994 merged PR #12225:
URL: https://github.com/apache/tvm/pull/12225
--
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.
junrushao 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 aeda760e5e [TIR] Disallow unused rhs vars in
This is an automated email from the ASF dual-hosted git repository.
xiyou 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 578ef035b2 Fix comments. (#12220)
578ef035b2 is
zxybazh merged PR #12220:
URL: https://github.com/apache/tvm/pull/12220
--
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:
alter-xp opened a new pull request, #12230:
URL: https://github.com/apache/tvm/pull/12230
create Dockerfile.ci_riscv
Move RISC-V related content from ci_qemu to ci_riscv
@areusch
--
This is an automated message from the Apache Git Service.
To respond to the message, please
zhang-yi-chi opened a new pull request, #12229:
URL: https://github.com/apache/tvm/pull/12229
Add GridSample operator for ONNX frontend.
cc @mbrookhart @AndrewZhaoLuo
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub
alter-xp closed pull request #12212: [ci][docker] create Dockerfile.ci_riscv
URL: https://github.com/apache/tvm/pull/12212
--
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
blackkker commented on code in PR #12028:
URL: https://github.com/apache/tvm/pull/12028#discussion_r932947473
##
tests/python/frontend/tflite/test_forward.py:
##
@@ -14,20 +14,30 @@
# KIND, either express or implied. See the License for the
# specific language governing
blackkker commented on code in PR #12028:
URL: https://github.com/apache/tvm/pull/12028#discussion_r932947473
##
tests/python/frontend/tflite/test_forward.py:
##
@@ -14,20 +14,30 @@
# KIND, either express or implied. See the License for the
# specific language governing
This is an automated email from the ASF dual-hosted git repository.
leandron 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 9a4d80c5fe Removing header arm_math.h which has
leandron merged PR #12217:
URL: https://github.com/apache/tvm/pull/12217
--
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:
heliqi commented on PR #12211:
URL: https://github.com/apache/tvm/pull/12211#issuecomment-1198933230
One suggestion: The title could be changed to "[Frontend] [Paddle] fix bug
..".
LGTM!
--
This is an automated message from the Apache Git Service.
To respond to the message, please
billishyahao opened a new pull request, #12228:
URL: https://github.com/apache/tvm/pull/12228
Mish activation function is widely used in object detection, like yolov4,
scaledYolov4. This patch is to enable dnnl to support conv+mish fusion. It will
bring huge performance boost varied from
crazydemo commented on code in PR #12151:
URL: https://github.com/apache/tvm/pull/12151#discussion_r932899385
##
tests/python/contrib/test_dnnl.py:
##
@@ -788,6 +789,44 @@ def test_conv2d_pattern(run_module, dtype="float32"):
run_and_verify_func(config,
crazydemo commented on code in PR #12151:
URL: https://github.com/apache/tvm/pull/12151#discussion_r932899255
##
python/tvm/relay/op/contrib/dnnl.py:
##
@@ -305,6 +395,12 @@ def pattern_table():
dnnl_patterns = list()
dnnl_patterns.append(make_qnn_conv2d_pattern())
crazydemo commented on code in PR #12151:
URL: https://github.com/apache/tvm/pull/12151#discussion_r932899094
##
tests/python/contrib/test_dnnl.py:
##
@@ -192,6 +192,7 @@ def run_and_verify(mod, input, params, target, run_module,
subgraph_num=None, te
if use_dnnl:
71 matches
Mail list logo