vizero1 opened a new pull request #4883: Use opencv reisze method for
preprocessing of image in darknet
URL: https://github.com/apache/incubator-tvm/pull/4883
Refactor preprocessing for darknet. Now the image processing is
approximately ten times faster.
See following issue for more
yongfeng-nv opened a new pull request #4885: Split node min range is not
stringent.
URL: https://github.com/apache/incubator-tvm/pull/4885
Previously, PassDownDomain always sets inner IterVar's extent to the split
factor, even when the parent extent is less than the factor (usually
lfengad opened a new pull request #4882: [Relay][Topi] Hashtable support
URL: https://github.com/apache/incubator-tvm/pull/4882
We observe a great amount of tensorflow NLP
models used in our production environment, and a lot of them use Hashtable
related operators for word/character
KindleHe opened a new issue #4884: [android_deploy] crash is caused by
`Module.load` func while running App on Android Device with
URL: https://github.com/apache/incubator-tvm/issues/4884
I install the apk in vivo X6S A, according to the [Android TVM
yongfeng-nv commented on issue #4885: Split node min range is not stringent.
URL: https://github.com/apache/incubator-tvm/pull/4885#issuecomment-586353936
@Hzfengsy , can you review this PR, at least the test I updated. Thank you.
tqchen commented on issue #4884: [android_deploy] CRASH caused by `Module.load`
func while running App on Android Device with
URL: https://github.com/apache/incubator-tvm/issues/4884#issuecomment-586361748
Can you see if https://github.com/apache/incubator-tvm/pull/4871 resolved
your
tqchen edited a comment on issue #4884: [android_deploy] CRASH caused by
`Module.load` func while running App on Android Device with
URL: https://github.com/apache/incubator-tvm/issues/4884#issuecomment-586361748
Can you see if https://github.com/apache/incubator-tvm/pull/4871 resolved
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586412142
@mbarrett97 @comaniac I just pushed a test where "result" creates an
incorrect graph, and
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586412142
@mbarrett97 @comaniac I just pushed a test where "result" creates an
incorrect graph, and
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586412142
@mbarrett97 @comaniac I just pushed a test where "result" creates an
incorrect graph, and
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586412142
@mbarrett97 @comaniac I just pushed a test where "result" creates an
incorrect graph, and "expected" is
merrymercy commented on a change in pull request #4870: [AutoTVM] Support range
in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#discussion_r379586297
##
File path: python/tvm/autotvm/tuner/index_based_tuner.py
##
@@ -0,0 +1,122 @@
+# Licensed
merrymercy commented on a change in pull request #4870: [AutoTVM] Support range
in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#discussion_r379586297
##
File path: python/tvm/autotvm/tuner/index_based_tuner.py
##
@@ -0,0 +1,122 @@
+# Licensed
comaniac commented on a change in pull request #4870: [AutoTVM] Support range
in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#discussion_r379544397
##
File path: python/tvm/autotvm/tuner/index_based_tuner.py
##
@@ -0,0 +1,121 @@
+# Licensed to
kumasento commented on a change in pull request #4847: Return empty
CSourceModule when no lowered_funcs exists in Relay mod
URL: https://github.com/apache/incubator-tvm/pull/4847#discussion_r379544814
##
File path: src/relay/backend/build_module.cc
##
@@ -437,28 +441,50
zhiics commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586428873
@soiferj hmm, this looks a bit wired to me, I will take a look at it. Thanks.
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586428127
Yes, they pass the alpha_equal check.
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586428127
Yes, they both pass the alpha_equal check.
tqchen commented on issue #4882: [Relay][Topi] Hashtable support
URL: https://github.com/apache/incubator-tvm/pull/4882#issuecomment-586359543
Thanks @lfengad for the PR. Given this PR involves a major technical
decisions(introducing hashtable to the runtime), can you please open discuss
tqchen edited a comment on issue #4882: [Relay][Topi] Hashtable support
URL: https://github.com/apache/incubator-tvm/pull/4882#issuecomment-586359543
Thanks @lfengad for the PR. Given this PR involves a major technical
decisions(introducing hashtable to the runtime), can you please open
slyubomirsky commented on issue #4881: [WIP] Fixing an Infinite Loop case in
UnmatchedChecker.
URL: https://github.com/apache/incubator-tvm/pull/4881#issuecomment-586429594
Excellent catch, thank you for finding a repro.
As we privately discussed, this appears to be a problem in
mbarrett97 commented on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586429654
You could try graph_equal which claims to check for data flow equivalency,
although I am a bit
mbarrett97 commented on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586364932
Good catch :) Fix looks to be correct, looking forward to the test case.
comaniac commented on a change in pull request #4870: [AutoTVM] Support range
in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#discussion_r379544397
##
File path: python/tvm/autotvm/tuner/index_based_tuner.py
##
@@ -0,0 +1,121 @@
+# Licensed to
mbrookhart opened a new pull request #4886: First pass a defining a
non-recursive Graph Vistor and Rewriter
URL: https://github.com/apache/incubator-tvm/pull/4886
@jroesch @tqchen
This is an automated message
tqchen commented on issue #4871: [JVM] Update the runtime PackedFunc for module
URL: https://github.com/apache/incubator-tvm/pull/4871#issuecomment-586364066
cc @yzhliu can we try to add a regression test that covers the related
functions?
comaniac commented on a change in pull request #4870: [AutoTVM] Support range
in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#discussion_r379544397
##
File path: python/tvm/autotvm/tuner/index_based_tuner.py
##
@@ -0,0 +1,121 @@
+# Licensed to
comaniac commented on a change in pull request #4870: [AutoTVM] Support range
in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#discussion_r379544397
##
File path: python/tvm/autotvm/tuner/index_based_tuner.py
##
@@ -0,0 +1,121 @@
+# Licensed to
anijain2305 commented on a change in pull request #4880: [QNN] Add support for
per channel weight scale in dense op
URL: https://github.com/apache/incubator-tvm/pull/4880#discussion_r379585753
##
File path: tests/python/relay/test_op_qnn_dense.py
##
@@ -75,52 +75,8 @@ def
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586412142
@mbarrett97 @comaniac I just pushed a test where "result" creates an
incorrect graph, and
zhiics commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586426900
@soiferj Sorry. I don't quite understand the problem. Do you mean that these
two expressions can pass
comaniac commented on a change in pull request #4870: [AutoTVM] Support range
in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#discussion_r379612779
##
File path: python/tvm/autotvm/tuner/index_based_tuner.py
##
@@ -0,0 +1,122 @@
+# Licensed to
zhiics edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586474522
graph equal would not make a difference here as it checks free vars.
masahi commented on issue #4880: [QNN] Add support for per channel weight scale
in dense op
URL: https://github.com/apache/incubator-tvm/pull/4880#issuecomment-586507666
ready to go @vinx13 @FrozenGene
This is an automated
zhiics edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586505085
hmm, I just tried this:
```python
import numpy as np
import tvm
from tvm import
zhiics edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586505085
hmm, I just tried this:
```python
import numpy as np
import tvm
from tvm import
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586469382
graph_equal also succeeds on the buggy graph :( @zhiics, let me know when
you have any findings!
mbrookhart commented on a change in pull request #4886: [WIP][POC]First pass a
defining at non-recursive Graph Vistor and Rewriter
URL: https://github.com/apache/incubator-tvm/pull/4886#discussion_r379618563
##
File path: include/tvm/relay/expr_functor.h
##
@@ -197,7
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586472422
I'll do some investigation :)
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586472422
I'll do some investigation :)
Update: in alpha_equal.cc, `relay._make._graph_equal` actually
mbrookhart commented on a change in pull request #4886: [WIP][POC]First pass a
defining at non-recursive Graph Vistor and Rewriter
URL: https://github.com/apache/incubator-tvm/pull/4886#discussion_r379618563
##
File path: include/tvm/relay/expr_functor.h
##
@@ -197,7
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586472422
I'll do some investigation :)
Update: in alpha_equal.cc, `relay._make._graph_equal` actually
icemelon9 edited a comment on issue #4644: Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#issuecomment-586483826
ci is green now.
Could you help review the PR? cc @tqchen @jwfromm @zhiics @ZihengJiang
@junrushao1994 @merrymercy @vinx13 @kevinthesun @comaniac
mbarrett97 commented on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586516413
So is the issue that the test case currently passes both pre and post fix?
If so, I'd say it probably
zhiics commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586474522
graph equal would not make a difference here as it checks free vars. I might
not have time today. I can
zhiics edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586474522
I might not have time today. I can spend some time on it over the weekend.
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586509270
That's really strange - it looks right. Are you able to pull my branch and
give the test a try?
zhiics commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586509927
I can give it a try over the weekend, but why do you feed the expected with
an unexpected expression?
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586512825
Sorry, what exactly do you mean?
This is
tqchen commented on a change in pull request #4886: [WIP][POC]First pass a
defining at non-recursive Graph Vistor and Rewriter
URL: https://github.com/apache/incubator-tvm/pull/4886#discussion_r379602582
##
File path: include/tvm/relay/expr_functor.h
##
@@ -197,7 +198,7
mbrookhart commented on a change in pull request #4886: [WIP][POC]First pass a
defining at non-recursive Graph Vistor and Rewriter
URL: https://github.com/apache/incubator-tvm/pull/4886#discussion_r379618563
##
File path: include/tvm/relay/expr_functor.h
##
@@ -197,7
anijain2305 commented on issue #4790: Fast exponent
URL: https://github.com/apache/incubator-tvm/pull/4790#issuecomment-586511407
Lets get this in - @tqchen
This is an automated message from the Apache Git Service.
To
zhiics edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586514793
I though you provided
```
v0.0.4
fn (%a: Tensor[(10, 10), float32], %b: Tensor[(10, 10),
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586515076
I think so. If everyone else is okay, I think it's best to check this fix in.
zhiics commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586514793
I though you provided
```
v0.0.4
fn (%a: Tensor[(10, 10), float32], %b: Tensor[(10, 10), float32])
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586472422
I'll do some investigation :)
This is an
comaniac commented on issue #4870: [AutoTVM] Support range in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#issuecomment-586476431
@merrymercy I've removed `__setstate__` and `__getstate__` from tuners
according to the discussion. The only one left is in `Task`
wpan11nv edited a comment on issue #4876: [CodeGen][CUDA] Fix issues in cuda
codegen
URL: https://github.com/apache/incubator-tvm/pull/4876#issuecomment-585914125
This patch should fix errors observed below (I did *not* verify as I found
no complete reproducers there). My own test works
zhiics commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586541570
Thanks for the effort. I will take a look later. So, do we still need to
flip the args? If so, we still
zhiics edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586541570
Thanks for the effort. I will take a look later. So, do we still need to
flip the args? If so, we
siju-samuel commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762561
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -792,6 +794,147 @@ def
siju-samuel commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762580
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -792,6 +794,147 @@ def
siju-samuel commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762146
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -244,6 +244,74 @@
siju-samuel commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762188
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -244,6 +244,74 @@
siju-samuel commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762709
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -244,6 +244,74 @@
siju-samuel commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762683
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -792,6 +794,147 @@ def
yongfeng-nv opened a new issue #4890: LoopVectorizer depends on ifthenelse
URL: https://github.com/apache/incubator-tvm/issues/4890
My PR (https://github.com/apache/incubator-tvm/pull/4885) is blocked by a
test failure
huajsj commented on issue #4887: [VTA] YoloV3 Support
URL: https://github.com/apache/incubator-tvm/pull/4887#issuecomment-586522965
After this patch, I can run Yolov3 tiny on VTA(simulator + FPGA), but it
still have some accuracy issue, It may caused by test application parameter
usage
comaniac opened a new pull request #4870: [AutoTVM] Support range in index
based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870
This PR includes the following changes in order to let grid search and
random tuner accept an index range. This is beneficial for distributed
comaniac commented on issue #4870: [AutoTVM] Support range in index based tuners
URL: https://github.com/apache/incubator-tvm/pull/4870#issuecomment-586523071
Re-trigger CI since it failed with no sense.
This is an automated
comaniac closed pull request #4870: [AutoTVM] Support range in index based
tuners
URL: https://github.com/apache/incubator-tvm/pull/4870
This is an automated message from the Apache Git Service.
To respond to the message,
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586521847
Actually, are you sure the second argument is expected? It looks like
AlphaEqual loops through the
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586527376
This is actually a good exercise, as some other tests are actually failing
now due to the graphs
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586527376
This is actually a good exercise, as some other tests are actually failing
now due to the graphs not
mbarrett97 commented on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586527273
So long as the test now correctly fails for the current behaviour, I'm
happy. The ordering mattering
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586529239
This test (test_branch_merge) is now failing at the de-duplicate pass. It's
interesting since the
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586529239
This test (test_branch_merge) is now failing at the de-duplicate pass. It's
interesting since the
slyubomirsky commented on issue #4864: [Relay] Ignore Primitive functions in
Visitors
URL: https://github.com/apache/incubator-tvm/pull/4864#issuecomment-586537964
I want to second @tqchen's comments: there are visitors (like the Python
converter or the Relay AoT compiler) that do operate
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586537875
Alright, sorry for all of the spam. All tests are now fixed. cc @zhiics
@mbarrett97
masahi opened a new pull request #4889: [Relay] Fix VM compiler for while loop
with free vars
URL: https://github.com/apache/incubator-tvm/pull/4889
This is a fix to the issue reported in
https://discuss.tvm.ai/t/a-relay-vm-question-while-loop-and-free-vars/5541/
It seems if a
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586521847
Actually, are you sure the second argument is expected? It looks like
AlphaEqual loops through the LHS
zhiics commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586526565
I am okay with it as the failure should be separate issue from
`alpha_equal`. But I would suggest we
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586529239
This test is now failing at the de-duplicate pass. It's interesting since
the "correct" graph has the
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586529239
This test (test_branch_merge) is now failing at the de-duplicate pass. It's
interesting since the
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586529239
This test is now failing at the de-duplicate pass. It's interesting since
the "correct" (result)
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586529239
This test (test_branch_merge) is now failing at the de-duplicate pass. It's
interesting since the
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586541787
It seems like we need to flip the args. I’ll open the issue on Monday.
vinx13 commented on issue #4876: [CodeGen][CUDA] Fix issues in cuda codegen
URL: https://github.com/apache/incubator-tvm/pull/4876#issuecomment-586542881
We can remove these lines
https://github.com/apache/incubator-tvm/blob/master/src/target/source/codegen_cuda.cc#L60-L73
vinx13 commented on issue #4876: [CodeGen][CUDA] Fix issues in cuda codegen
URL: https://github.com/apache/incubator-tvm/pull/4876#issuecomment-586542924
also cc @yzhliu @zxy844288792
This is an automated message from the
masahi opened a new pull request #4888: improve antlr import error message
URL: https://github.com/apache/incubator-tvm/pull/4888
Currently, the error message I get from the parser import failure is
confusing.
If I try to use VM functionality, I get an error `Couldn't find ANTLR
wpan11nv commented on issue #4876: [CodeGen][CUDA] Fix issues in cuda codegen
URL: https://github.com/apache/incubator-tvm/pull/4876#issuecomment-586550799
Updated the patch as suggested. Thanks!
This is an automated message
This is an automated email from the ASF dual-hosted git repository.
lmzheng pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/master by this push:
new feda150 [AutoTVM] Support range in
merrymercy merged pull request #4870: [AutoTVM] Support range in index based
tuners
URL: https://github.com/apache/incubator-tvm/pull/4870
This is an automated message from the Apache Git Service.
To respond to the message,
Hzfengsy commented on a change in pull request #4885: Split node min range is
not stringent.
URL: https://github.com/apache/incubator-tvm/pull/4885#discussion_r379769004
##
File path: src/te/schedule/message_passing.cc
##
@@ -62,6 +62,13 @@ void PassDownDomain(const
huajsj opened a new pull request #4887: [VTA] YoloV3 Support
URL: https://github.com/apache/incubator-tvm/pull/4887
Issue:
YoloV3 use some operator and logic that not get good support by
existing vta logic, like nn.pad, upsample, and 255 output channel.
Solution:
add related
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586525810
If I flip the arguments to alpha_equals and properly add the attributes to
the "expected" function, the
soiferj edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586527376
This is actually a good exercise, as some other tests are actually failing
now due to the graphs
zhiics commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586527810
@soiferj Can you also try to create a minimal example? Thanks.
soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call
node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586527594
Thanks everyone for working through this with me!
zhiics edited a comment on issue #4879: [Relay][Pass] Fix bug in re-processing
call node in MergeComposite pass
URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586527810
@soiferj Can you also try to create a minimal counterexample? Thanks.
1 - 100 of 112 matches
Mail list logo