fantasyRqg commented on pull request #7211:
URL: https://github.com/apache/tvm/pull/7211#issuecomment-754468357
```log
enabled targets: llvm -device=arm_cpu; llvm
pytest marker:
== test
session starts
merrymercy commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551763767
##
File path: python/tvm/auto_scheduler/cost_model/xgb_model.py
##
@@ -116,12 +117,17 @@ def __init__(self, verbose_eval=25,
num_warmup_sample=100, seed=N
merrymercy commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551763123
##
File path: python/tvm/auto_scheduler/task_scheduler.py
##
@@ -82,11 +82,12 @@ def make_search_policies(
if isinstance(search_policy, str):
FrozenGene commented on pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#issuecomment-754430231
Thanks for the great work @leowang1225 and thanks for the reviewing @jcf94 ,
it is merged now.
This is an automa
This is an automated email from the ASF dual-hosted git repository.
zhaowu pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from d052752 [ConvertLayout] slice_like support (#7184)
add 23bd825 [AutoScheduler] Add custom build function (#7185)
N
FrozenGene merged pull request #7185:
URL: https://github.com/apache/tvm/pull/7185
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 t
masahi edited a comment on pull request #7208:
URL: https://github.com/apache/tvm/pull/7208#issuecomment-754410295
Hi @luyaor you are welcome to poke at pytorch frontend too, I hope it is
more robust than onnx frontend :)
Th
masahi commented on pull request #7208:
URL: https://github.com/apache/tvm/pull/7208#issuecomment-754410295
Hi @luyaor you are welcome to poke at pytorch frontend too, I hope it is
more robust then onnx frontend :)
This is a
jwfromm commented on pull request #7208:
URL: https://github.com/apache/tvm/pull/7208#issuecomment-754406762
These two errors that you generated were excellent real bugs with the
importer and were very easy to understand and replicate with your post. If
they're being auto-generated they lo
fantasyRqg opened a new pull request #7211:
URL: https://github.com/apache/tvm/pull/7211
Deploy models on Android & iOS platform must use system-lib. Avoid usage of
`dlopen`.
[bundle_deploy](https://github.com/apache/tvm/tree/main/apps/bundle_deploy)
demonstrated how to deploy a model
luyaor edited a comment on pull request #7208:
URL: https://github.com/apache/tvm/pull/7208#issuecomment-754398110
Hi @jwfromm @mbrookhart , thanks for the response and effort on this case.
The PR looks good to me.
I am currently working on a research project related to TVM, would li
luyaor commented on pull request #7208:
URL: https://github.com/apache/tvm/pull/7208#issuecomment-754398110
Hi @jwfromm @mbrookhart , thanks for the response and effort on this case.
The PR looks good to me.
I am currently working on the research project related to TVM, would like to
masahi opened a new pull request #7210:
URL: https://github.com/apache/tvm/pull/7210
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful information and tips. After
the pull request is submitted, please request code reviews from
[
insop commented on issue #7186:
URL: https://github.com/apache/tvm/issues/7186#issuecomment-754387174
For `_npi_stack ` : https://github.com/apache/tvm/pull/7209 is submitted.
This is an automated message from the Apache Git
insop opened a new pull request #7209:
URL: https://github.com/apache/tvm/pull/7209
- https://github.com/apache/tvm/issues/7186
- add MxNet stack, `_npi_stack`
-
https://mxnet.apache.org/versions/master/api/python/docs/api/np/generated/mxnet.np.stack.html?highlight=stack
@junru
jwfromm commented on issue #7203:
URL: https://github.com/apache/tvm/issues/7203#issuecomment-754380843
This bug is also fixed in #7208 and was caused by the same issue as #7202.
This is an automated message from the Apache G
jwfromm commented on issue #7202:
URL: https://github.com/apache/tvm/issues/7202#issuecomment-754372403
Thanks for finding this bug, it's due to a bad assumption made in Prelu
conversion about the input layout. The issue is fixed in
https://github.com/apache/tvm/pull/7208 and I've confirme
jwfromm commented on pull request #7208:
URL: https://github.com/apache/tvm/pull/7208#issuecomment-754372193
@luyaor @mbrookhart @masahi can you guys take a look at this tiny PR?
This is an automated message from the Apache G
jwfromm opened a new pull request #7208:
URL: https://github.com/apache/tvm/pull/7208
Our current prelu converter assumes that incoming data is in NCHW format and
that the slope will have C total elements. Neither of these are actual
requirements for ONNX PreLu. As pointed out in
https://
insop commented on a change in pull request #7164:
URL: https://github.com/apache/tvm/pull/7164#discussion_r551695870
##
File path: docs/dev/index.rst
##
@@ -396,3 +396,11 @@ Security
:maxdepth: 1
security
+
+
+microTVM
+-
+.. toctree::
Review comment:
aaltonenzhang edited a comment on issue #7196:
URL: https://github.com/apache/tvm/issues/7196#issuecomment-754362026
@insop reedited the url links for both of the two issues.
This is an automated message from the Apache Git S
aaltonenzhang commented on issue #7196:
URL: https://github.com/apache/tvm/issues/7196#issuecomment-754362026
@insop reedited the url link for both of the two issues.
This is an automated message from the Apache Git Service.
aaltonenzhang removed a comment on issue #7196:
URL: https://github.com/apache/tvm/issues/7196#issuecomment-754320776
@insop It seems that there are something wrong when you click the url, but
you can copy and paste it to your browser. And for the issue #7198, it's also
created by me, but
leowang1225 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551682259
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -303,12 +315,28 @@ class LocalBuilder(ProgramBuilder):
This is used in a wrapper of the
FrozenGene commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551678095
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -303,12 +315,28 @@ class LocalBuilder(ProgramBuilder):
This is used in a wrapper of the m
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551675372
##
File path: src/runtime/graph/debug/graph_runtime_debug.cc
##
@@ -153,9 +153,10 @@ class GraphRuntimeDebug : public GraphRuntime {
const TVMContext& ctx
jcf94 opened a new issue #7207:
URL: https://github.com/apache/tvm/issues/7207
This bug was introduced in #6964 .
Currently, use graph debug runtime will get wrong time result.
Cause:
https://github.com/apache/tvm/blob/d05275298d9e630af6d8ff958753fd010759935c/src/runtime/graph/
icemelon9 commented on a change in pull request #7120:
URL: https://github.com/apache/tvm/pull/7120#discussion_r551668826
##
File path: include/tvm/relay/dataflow_pattern.h
##
@@ -46,6 +48,29 @@ class DFPatternNode : public Object {
*/
class DFPattern : public ObjectRef {
comaniac commented on pull request #7184:
URL: https://github.com/apache/tvm/pull/7184#issuecomment-754323779
Thanks @anijain2305 !
This is an automated message from the Apache Git Service.
To respond to the message, please l
This is an automated email from the ASF dual-hosted git repository.
comaniac 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 d052752 [ConvertLayout] slice_like support (#7184)
d
comaniac merged pull request #7184:
URL: https://github.com/apache/tvm/pull/7184
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
areusch commented on pull request #7164:
URL: https://github.com/apache/tvm/pull/7164#issuecomment-754322902
@insop @tqchen thanks for reviewing, please take another look when you have
a minute.
This is an automated message
aaltonenzhang commented on issue #7196:
URL: https://github.com/apache/tvm/issues/7196#issuecomment-754320776
@insop It seems that there are something wrong when you click the url, but
you can copy and paste it to your browser. And for the issue #7198, it's also
created by me, but they ar
areusch commented on a change in pull request #7164:
URL: https://github.com/apache/tvm/pull/7164#discussion_r551658809
##
File path: docs/dev/index.rst
##
@@ -396,3 +396,11 @@ Security
:maxdepth: 1
security
+
+
+microTVM
+-
+.. toctree::
Review comment:
areusch commented on a change in pull request #7164:
URL: https://github.com/apache/tvm/pull/7164#discussion_r551658680
##
File path: docs/dev/microtvm_design.rst
##
@@ -0,0 +1,340 @@
+.. Licensed to the Apache Software Foundation (ASF) under one
+or more contributor licen
areusch commented on a change in pull request #7164:
URL: https://github.com/apache/tvm/pull/7164#discussion_r551656029
##
File path: docs/dev/microtvm_design.rst
##
@@ -0,0 +1,340 @@
+.. Licensed to the Apache Software Foundation (ASF) under one
+or more contributor licen
areusch commented on a change in pull request #7164:
URL: https://github.com/apache/tvm/pull/7164#discussion_r551655848
##
File path: docs/dev/microtvm_design.rst
##
@@ -0,0 +1,340 @@
+.. Licensed to the Apache Software Foundation (ASF) under one
+or more contributor licen
comaniac commented on pull request #7184:
URL: https://github.com/apache/tvm/pull/7184#issuecomment-754279843
Kindly remind @anijain2305 @yzhliu for reviewing this PR :)
This is an automated message from the Apache Git Servic
mbrookhart commented on pull request #7172:
URL: https://github.com/apache/tvm/pull/7172#issuecomment-754276271
Kudos!
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitH
lhutton1 commented on a change in pull request #7206:
URL: https://github.com/apache/tvm/pull/7206#discussion_r551595603
##
File path: python/tvm/relay/op/contrib/arm_compute_lib.py
##
@@ -19,12 +19,15 @@
import numpy as np
import tvm
+import tvm._ffi
Review comment:
comaniac commented on pull request #7205:
URL: https://github.com/apache/tvm/pull/7205#issuecomment-754249830
Thanks @trevor-m @junrushao1994
This is an automated message from the Apache Git Service.
To respond to the messag
This is an automated email from the ASF dual-hosted git repository.
comaniac 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 7163b5c ReshapeAttrs no longer has reverse (#7205)
7
comaniac merged pull request #7205:
URL: https://github.com/apache/tvm/pull/7205
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
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/tvm-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 5581d5b Build at Mon Jan 4 16:23:05 EST
comaniac commented on pull request #7194:
URL: https://github.com/apache/tvm/pull/7194#issuecomment-754218139
Thanks @masahi @kevinthesun
This is an automated message from the Apache Git Service.
To respond to the message, p
This is an automated email from the ASF dual-hosted git repository.
comaniac pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 7053235 Fixed temporary lock_guard instances. (#7199)
add 361f508 [CUBLAS, CUDNN] Support dynamic batch size (#71
comaniac merged pull request #7194:
URL: https://github.com/apache/tvm/pull/7194
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
masahi edited a comment on pull request #7195:
URL: https://github.com/apache/tvm/pull/7195#issuecomment-754199021
@mbrookhart I have a fast-path for one segment case, so the perf is the same
between current / new. I'll update the condition to work for dimension other
than two.
https:/
masahi commented on pull request #7195:
URL: https://github.com/apache/tvm/pull/7195#issuecomment-754199021
@mbrookhart I have a fast-path for one segment case, so the perf is the same
between current / new. I'll update the condition to work for dimension other
then two.
https://github
d-smirnov opened a new pull request #7206:
URL: https://github.com/apache/tvm/pull/7206
Added support for depthwise convolution. ACL only supports depth-wise
convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2),
if this is not the case then fallback to TVM.
A
trevor-m commented on pull request #7195:
URL: https://github.com/apache/tvm/pull/7195#issuecomment-754151980
Nice! Have you also looked at CUB's
[DeviceSegmentedRadixSort::SortPairsDescending](https://nvlabs.github.io/cub/structcub_1_1_device_segmented_radix_sort.html#abbba6639f928bebd1943
trevor-m opened a new pull request #7205:
URL: https://github.com/apache/tvm/pull/7205
Updates TRT converter for Reshape op after
https://github.com/apache/tvm/pull/7086 removed `reverse` attr.
This is an automated message f
d-smirnov commented on pull request #6998:
URL: https://github.com/apache/tvm/pull/6998#issuecomment-754128584
bump cc @siju-samuel @FrozenGene
Please, also advise on extra check to _assert_allclose_
This is an automated m
comaniac commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551479201
##
File path: src/auto_scheduler/feature.cc
##
@@ -1462,12 +1462,18 @@ void GetPerStoreFeaturesFromMeasurePairs(const
Array& inputs,
if (find_res == ta
areusch commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551452806
##
File path: src/runtime/graph/debug/graph_runtime_debug.cc
##
@@ -153,9 +153,10 @@ class GraphRuntimeDebug : public GraphRuntime {
const TVMContext& ct
mbrookhart commented on pull request #7195:
URL: https://github.com/apache/tvm/pull/7195#issuecomment-754096681
Also, I think you and I are using different versions of CUDA for the same
GPU, that might explain the difference in the numbers I posted in #7099 and you
posted here.
-
mbrookhart commented on pull request #7195:
URL: https://github.com/apache/tvm/pull/7195#issuecomment-754095011
This looks great. My only concern would possibly be that some object
detection models (I'm thinking gluon SSD) have a very large number of boxes
they sort before NMS. Could you a
mbrookhart commented on a change in pull request #7125:
URL: https://github.com/apache/tvm/pull/7125#discussion_r551422829
##
File path: include/tvm/topi/transform.h
##
@@ -1386,6 +1386,88 @@ inline Array meshgrid(const Array&
inputs, const std::string& in
return result;
}
junrushao1994 commented on issue #7204:
URL: https://github.com/apache/tvm/issues/7204#issuecomment-754021201
It is not an error actually. In our CI pipeline, we can see this message on
the beginning of every stage...
This i
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 7053235 Fixed temporary lock_guard instances. (#7199)
tqchen merged pull request #7199:
URL: https://github.com/apache/tvm/pull/7199
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 s
rhzhang1995 opened a new issue #7204:
URL: https://github.com/apache/tvm/issues/7204
When I was using Alveo U50 to configure TVM, I entered command
“./tvm/docker/build.sh demo_vitis_ai bash”, and finally 2“mesg: ttyname failed:
Inappropriate ioctl for device” appeared. Is TVM incompatible
luyaor opened a new issue #7203:
URL: https://github.com/apache/tvm/issues/7203
## Description
When compiling following model with TVM, it will error.
The model(with ONNX as frontend) with error is as follows, check bug.onnx in
[bug3.zip](https://github.com/apache/tvm/files/57
luyaor opened a new issue #7202:
URL: https://github.com/apache/tvm/issues/7202
## Description
When compiling following model with TVM, it will error.
The model(with ONNX as frontend) with error is as follows, check bug.onnx in
bug2.zip.
 with error is as follows, check
luyaor opened a new issue #7200:
URL: https://github.com/apache/tvm/issues/7200
## Description
When compiling following model with opt_level=2, TVM will crash. While if
turn opt_level to 3, it will run normally.
The model(with ONNX as frontend) with error is as follows, check
kalman5 edited a comment on pull request #7199:
URL: https://github.com/apache/tvm/pull/7199#issuecomment-753911981
For reviewers @jcf94 @ZihengJiang
This is an automated message from the Apache Git Service.
To respond to th
kalman5 commented on pull request #7199:
URL: https://github.com/apache/tvm/pull/7199#issuecomment-753911981
@jcf94
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub
kalman5 opened a new pull request #7199:
URL: https://github.com/apache/tvm/pull/7199
This diff fixes the temporary lock_guard instances giving those a name.
This is an automated message from the Apache Git Service.
To re
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551211822
##
File path: python/tvm/auto_scheduler/cost_model/xgb_model.py
##
@@ -141,6 +146,12 @@ def update(self, inputs, results):
self.inputs.extend(inputs)
FrozenGene commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551215468
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread.
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551211822
##
File path: python/tvm/auto_scheduler/cost_model/xgb_model.py
##
@@ -141,6 +146,12 @@ def update(self, inputs, results):
self.inputs.extend(inputs)
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551211822
##
File path: python/tvm/auto_scheduler/cost_model/xgb_model.py
##
@@ -141,6 +146,12 @@ def update(self, inputs, results):
self.inputs.extend(inputs)
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551211822
##
File path: python/tvm/auto_scheduler/cost_model/xgb_model.py
##
@@ -141,6 +146,12 @@ def update(self, inputs, results):
self.inputs.extend(inputs)
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551211822
##
File path: python/tvm/auto_scheduler/cost_model/xgb_model.py
##
@@ -141,6 +146,12 @@ def update(self, inputs, results):
self.inputs.extend(inputs)
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551211822
##
File path: python/tvm/auto_scheduler/cost_model/xgb_model.py
##
@@ -141,6 +146,12 @@ def update(self, inputs, results):
self.inputs.extend(inputs)
leowang1225 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551207425
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread
leowang1225 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551207425
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread
leowang1225 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551207425
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551206249
##
File path: src/auto_scheduler/feature.cc
##
@@ -1462,12 +1462,18 @@ void GetPerStoreFeaturesFromMeasurePairs(const
Array& inputs,
if (find_res == task_
jcf94 commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551206249
##
File path: src/auto_scheduler/feature.cc
##
@@ -1462,12 +1462,18 @@ void GetPerStoreFeaturesFromMeasurePairs(const
Array& inputs,
if (find_res == task_
insop commented on issue #7196:
URL: https://github.com/apache/tvm/issues/7196#issuecomment-753866375
@aaltonenzhang
Nit, it seems the embedded url
(https://github.com/tensorflow/models/tree/master/community) in the above post
is not the actual url shown, i.e. if you click the link you
comaniac commented on a change in pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#discussion_r551199732
##
File path: python/tvm/auto_scheduler/task_scheduler.py
##
@@ -82,11 +82,12 @@ def make_search_policies(
if isinstance(search_policy, str):
p
jcf94 commented on pull request #7197:
URL: https://github.com/apache/tvm/pull/7197#issuecomment-753862836
Thanks! @junrushao1994
Also cc @merrymercy @comaniac
This is an automated message from the Apache Git Service.
To
comaniac commented on pull request #7193:
URL: https://github.com/apache/tvm/pull/7193#issuecomment-753861130
Thanks @codeislife99 @junrushao1994
This is an automated message from the Apache Git Service.
To respond to the me
This is an automated email from the ASF dual-hosted git repository.
comaniac 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 eb64e25 Fix ICHECK_NOTNULL in logging.g (#7193)
eb64
comaniac merged pull request #7193:
URL: https://github.com/apache/tvm/pull/7193
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
leowang1225 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551195931
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread
aaltonenzhang opened a new issue #7198:
URL: https://github.com/apache/tvm/issues/7198
When testing tensorflow models from tfhub at [https://tfhub.dev/](url), I
found issues when import tensorflow IRs.
1. When I import saved model using TFParser.parse() and from_tensorflow(), I
found th
jcf94 opened a new pull request #7197:
URL: https://github.com/apache/tvm/pull/7197
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
jcf94 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551179115
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread.
jcf94 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551179115
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread.
aaltonenzhang opened a new issue #7196:
URL: https://github.com/apache/tvm/issues/7196
I'm checking tensorflow models from tensorflow models garden at
[https://github.com/tensorflow/models/tree/master/community](url).
For community models, there are types and operators which tvm doesn't
liangfu commented on pull request #7190:
URL: https://github.com/apache/tvm/pull/7190#issuecomment-753837813
Thanks @cxcxcxcx for the proposed change. This is now merged.
This is an automated message from the Apache Git Servi
This is an automated email from the ASF dual-hosted git repository.
liangfu pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 86a8504 [Frontend][MXNet] add _npi_subtract_scalar (#7191)
add 25f0252 Makes sure g_last_error is null terminated.
liangfu merged pull request #7190:
URL: https://github.com/apache/tvm/pull/7190
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
liangfu commented on a change in pull request #7190:
URL: https://github.com/apache/tvm/pull/7190#discussion_r551175687
##
File path: src/runtime/crt/common/crt_runtime_api.c
##
@@ -38,7 +38,10 @@
static char g_last_error[1024];
-void TVMAPISetLastError(const char* msg) {
leowang1225 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551170406
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread
leowang1225 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551170406
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread
leowang1225 commented on a change in pull request #7185:
URL: https://github.com/apache/tvm/pull/7185#discussion_r551170406
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -624,12 +652,10 @@ def local_build_worker(args):
The build result of this Builder thread
1 - 100 of 105 matches
Mail list logo
