FrozenGene edited a comment on issue #5355:
URL: https://github.com/apache/incubator-tvm/pull/5355#issuecomment-617571690
Thanks @u99127 @siju-samuel !
This is an automated message from the Apache Git Service.
To respond to
FrozenGene commented on issue #5355:
URL: https://github.com/apache/incubator-tvm/pull/5355#issuecomment-617571690
Thanks @u99127 @u99127 !
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.
zhaowu 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 3e3ccce Factor out import of common tfli
gopinath-r edited a comment on issue #5133:
URL: https://github.com/apache/incubator-tvm/issues/5133#issuecomment-617568268
@siju-samuel thanks for the reply
These are the values of input and input_types in repeat
**input>>> bound method Kernel.raw_input of
input_types>>> ['f
gopinath-r commented on issue #5133:
URL: https://github.com/apache/incubator-tvm/issues/5133#issuecomment-617568268
@siju-samuel thanks for the reply
These are the values of input and input_types in repeat
**input>>>
input_types>>> ['float', 'ListType']
data>>> tensor([[[0
icemelon9 opened a new pull request #5403:
URL: https://github.com/apache/incubator-tvm/pull/5403
Fix #5337
@tqchen @zhiics
This is an automated message from the Apache Git Service.
To respond to the message, please
tqchen commented on issue #5337:
URL: https://github.com/apache/incubator-tvm/pull/5337#issuecomment-617553469
Good catch @icemelon9 can you send another PR?
This is an automated message from the Apache Git Service.
To respon
icemelon9 commented on issue #5337:
URL: https://github.com/apache/incubator-tvm/pull/5337#issuecomment-617537724
@tqchen You forgot to remove PrintIR in the Relay transform header.
https://github.com/apache/incubator-tvm/blob/00014e20c3cc077727d467a67d3498260627e4e0/include/tvm/relay/tr
FrozenGene commented on issue #5380:
URL: https://github.com/apache/incubator-tvm/pull/5380#issuecomment-617534456
Thanks @siju-samuel
This is an automated message from the Apache Git Service.
To respond to the message, plea
This is an automated email from the ASF dual-hosted git repository.
zhaowu pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from ef61fd5 [LLVM] Use ArrayRef in calls to CreateShuffleVector
(#5399)
add 24f6865 [KERAS]Minimum & Alpha
FrozenGene commented on issue #5355:
URL: https://github.com/apache/incubator-tvm/pull/5355#issuecomment-617533538
@siju-samuel could you help to review it again?
This is an automated message from the Apache Git Service.
To r
tqchen commented on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617532455
i don't know unless we go and dig deeper, but if the bug is reproducible,
then it should not be hard to find the cause
-
hudmgy commented on issue #856:
URL: https://github.com/apache/incubator-tvm/issues/856#issuecomment-617530826
> btw, this generated .dll file works well when I call it using tvm's python
API.
hello, When I generated .dll file using
"lib.export_library('path/to/deploy_lib.dll')", I
hudmgy opened a new issue #5402:
URL: https://github.com/apache/incubator-tvm/issues/5402
when I ran "lib.export_library('path/to/deploy_lib.dll')" on windows, I
failed
cl: Command line warning D9024 :unrecognized source file
type“C:\Users\afx-\AppData\Local\Temp\tmprr0gougm\lib0.
tqchen opened a new pull request #5401:
URL: https://github.com/apache/incubator-tvm/pull/5401
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL abov
trivialfis commented on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617509251
Is it possible that somehow XGBoost linked a wrong dmlc static library?
This is an automated message from th
tqchen commented on issue #5357:
URL: https://github.com/apache/incubator-tvm/pull/5357#issuecomment-617507224
cc @icemelon9 @yzhliu @anijain2305
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.
tqchen 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 ef61fd5 [LLVM] Use ArrayRef in calls to
tqchen commented on issue #5398:
URL: https://github.com/apache/incubator-tvm/pull/5398#issuecomment-617505301
@kparzysz-quic please rebase against the master
This is an automated message from the Apache Git Service.
To respo
tqchen edited a comment on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617494614
The trace might offer some insights, @hcho3 , couldit caused by
ConfigureGpuId? also cc @trivialfis since it seems to relates to
https://github.com/dmlc/xgboost/pull/4961
tqchen commented on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617494614
The trace might offer some insights, @hcho3 , couldit caused by
ConfigureGpuId?
```
0x7fffb5ba9e37 in std::vector,
std::allocator > >
xgboost::XGBoostParameter::Updat
hcho3 commented on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617492866
Let me try again with `TVM_FFI=ctypes` environment variable set. What does
this do?
This is an automated message
areusch edited a comment on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617491801
I see this reliably with a virtualenv on bionic on AWS.
environment:
ami:
`099720109477/ubuntu/images/hvm-ssd/ubuntu-bionic-18.04-amd64-server-20200408`
usin
areusch commented on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617491801
I see this reliably with a virtualenv on bionic on AWS.
environment:
ami:
`099720109477/ubuntu/images/hvm-ssd/ubuntu-bionic-18.04-amd64-server-20200408`
python
tqchen opened a new pull request #5400:
URL: https://github.com/apache/incubator-tvm/pull/5400
Substitute now takes a std::function to customize more replacing behaviors.
Co-authored-by: Siyuan Feng
This i
tqchen commented on issue #5400:
URL: https://github.com/apache/incubator-tvm/pull/5400#issuecomment-617485403
cc @Hzfengsy @yzhliu @ZihengJiang
This is an automated message from the Apache Git Service.
To respond to the mes
tqchen edited a comment on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617475038
@leandron can you also provide a bit more details
e.g. does directly run `tests/python/unittest/test_autotvm_xgboost_model.py`
fails or do we need to run the entire
tqchen commented on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-617475038
@leandron can you also provide a bit more details
e.g. does directly run `tests/python/unittest/test_autotvm_xgboost_model.py`
fails or do we need to run the entire unitte
kparzysz-quic opened a new pull request #5399:
URL: https://github.com/apache/incubator-tvm/pull/5399
This switch was made in LLVM 11. Previously this function was expecting mask
indices of type `uint32_t`. This variant is now deprecated.
--
kparzysz-quic opened a new pull request #5398:
URL: https://github.com/apache/incubator-tvm/pull/5398
This function has recently been removed from LLVM 11. Use alternative way to
obtain vector element count (`VectorType::getNumElements`), which works for all
LLVM versions.
--
hlu1 commented on issue #5381:
URL: https://github.com/apache/incubator-tvm/pull/5381#issuecomment-617442169
I don't think you need to implement a non-copy version of set_output if you
simply want to avoid copy. `GetOutput` returns a NDArray, which is essentially
a shared_ptr to the underl
tqchen edited a comment on issue #5388:
URL: https://github.com/apache/incubator-tvm/issues/5388#issuecomment-617430228
CUDA's runtime API cudaFree implicitly syncs the default stream
This is an automated message from the Apa
tqchen commented on issue #5388:
URL: https://github.com/apache/incubator-tvm/issues/5388#issuecomment-617430228
CUDA's cudaFree implicitly syncs the default stream
This is an automated message from the Apache Git Service.
To
samwyi edited a comment on issue #5388:
URL: https://github.com/apache/incubator-tvm/issues/5388#issuecomment-617424509
> Thanks @samwyi for reporting the problem. Perhaps an easier fix now would
be call into Synchronize directly in when FreeDataSpace is called. This is also
the default be
samwyi commented on issue #5388:
URL: https://github.com/apache/incubator-tvm/issues/5388#issuecomment-617424509
> Thanks @samwyi for reporting the problem. Perhaps an easier fix now would
be call into Synchronize directly in when FreeDataSpace is called. This is also
the default behavior
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 d327787 [PTYTHON] Migrate VTA TIR passes
cbalint13 commented on a change in pull request #5395:
URL: https://github.com/apache/incubator-tvm/pull/5395#discussion_r412425014
##
File path: python/tvm/relay/op/_tensor_grad.py
##
@@ -61,6 +61,24 @@ def log_grad(orig, grad):
return [grad * ones_like(x) / x]
+@regi
tqchen edited a comment on issue #5397:
URL: https://github.com/apache/incubator-tvm/pull/5397#issuecomment-617351149
cc @tmoreau89 @ZihengJiang @zhiics
This is an automated message from the Apache Git Service.
To respond t
tqchen commented on issue #5397:
URL: https://github.com/apache/incubator-tvm/pull/5397#issuecomment-617351149
cc @tmoreau89 @ZihengJiang
This is an automated message from the Apache Git Service.
To respond to the message,
tqchen opened a new pull request #5397:
URL: https://github.com/apache/incubator-tvm/pull/5397
The new pass returns every pass as transform.Pass which allows
IRModule->IRModule transform.
cc @tmoreau89
This is an aut
tqchen edited a comment on issue #5362:
URL: https://github.com/apache/incubator-tvm/pull/5362#issuecomment-617340606
OK, let us wait for the mxnet-mkl then, currently blocked by
https://github.com/apache/incubator-tvm/issues/5396 hopefully we can land this
week
-
tqchen commented on issue #5362:
URL: https://github.com/apache/incubator-tvm/pull/5362#issuecomment-617340606
OK, let us wait for the mxnet-mkl then, currently blocked by
https://github.com/apache/incubator-tvm/issues/5396
tqchen opened a new issue #5396:
URL: https://github.com/apache/incubator-tvm/issues/5396
This issue happens when the docker update status for ci-gpu to the
lastest(the main change is is mkl-ml). Given these warnings, perhaps we need to
migrate
Currently block on sphinx pre-check w
siju-samuel opened a new pull request #5395:
URL: https://github.com/apache/incubator-tvm/pull/5395
- cosh
- sinh
- log2
- log10
- log1p
The ops are supported from relay and pytorch frontend.
@masahi please help me to review this PR. Thanks in advance.
--
anijain2305 edited a comment on issue #5394:
URL: https://github.com/apache/incubator-tvm/pull/5394#issuecomment-617284954
LGTM.
@inadob Is there any way to add a test? Do you have any suggestions here?
This is an aut
anijain2305 commented on issue #5394:
URL: https://github.com/apache/incubator-tvm/pull/5394#issuecomment-617284954
LGTM. Is there any way to add a test?
@inadob Do you have any suggestions here?
This is an automated
anijain2305 edited a comment on issue #5362:
URL: https://github.com/apache/incubator-tvm/pull/5362#issuecomment-617279905
@masahi @tqchen The MXNet quantized models has operators that can only work
with MKLDNN. Example is as follows. Note the `"op": "_sg_mkldnn_conv",`
~~~
{
anijain2305 commented on issue #5362:
URL: https://github.com/apache/incubator-tvm/pull/5362#issuecomment-617279905
@masahi @tqchen The MXNet quantized models has operators that can only work
with MKLDNN. Example is as follows. Note the `"op": "_sg_mkldnn_conv",`
~~~
{
"o
siju-samuel commented on issue #5133:
URL: https://github.com/apache/incubator-tvm/issues/5133#issuecomment-617272162
@gopinath-r can you please share the script to run from bts github or
scripted_model?
In `repeat`, can u please print both `inputs, input_types` and share the
result.
FrozenGene commented on issue #5215:
URL: https://github.com/apache/incubator-tvm/issues/5215#issuecomment-617256430
> @FrozenGene what is the status of this issue?
This issue wants to track all template of using `debug_skip_region`(like arm
/ cuda and so on). Currently, we only fix
tqchen commented on issue #5362:
URL: https://github.com/apache/incubator-tvm/pull/5362#issuecomment-617234125
We can just use the floating pt model for the reference pt
This is an automated message from the Apache Git Servic
tqchen commented on issue #5215:
URL: https://github.com/apache/incubator-tvm/issues/5215#issuecomment-617232476
@FrozenGene what is the status of this issue?
This is an automated message from the Apache Git Service.
To respo
tqchen edited a comment on issue #5373:
URL: https://github.com/apache/incubator-tvm/issues/5373#issuecomment-617230692
Thanks @kevinthesun , it should take about an hour
This is an automated message from the Apache Git Servi
tqchen commented on issue #5373:
URL: https://github.com/apache/incubator-tvm/issues/5373#issuecomment-617230692
Thanks @kevinthesun , it should take about a few hours
This is an automated message from the Apache Git Service.
adobay commented on a change in pull request #5289:
URL: https://github.com/apache/incubator-tvm/pull/5289#discussion_r412253968
##
File path: topi/include/topi/transform.h
##
@@ -1105,6 +1105,88 @@ inline tvm::te::Tensor matmul(const tvm::te::Tensor& A,
return tvm::te::comp
adobay commented on a change in pull request #5289:
URL: https://github.com/apache/incubator-tvm/pull/5289#discussion_r412253968
##
File path: topi/include/topi/transform.h
##
@@ -1105,6 +1105,88 @@ inline tvm::te::Tensor matmul(const tvm::te::Tensor& A,
return tvm::te::comp
adobay commented on a change in pull request #5289:
URL: https://github.com/apache/incubator-tvm/pull/5289#discussion_r412253968
##
File path: topi/include/topi/transform.h
##
@@ -1105,6 +1105,88 @@ inline tvm::te::Tensor matmul(const tvm::te::Tensor& A,
return tvm::te::comp
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 72f2aea Tf2 test fixups (#5391)
72f2aea
tqchen commented on issue #5391:
URL: https://github.com/apache/incubator-tvm/pull/5391#issuecomment-617228512
THanks @u99127 @siju-samuel
This is an automated message from the Apache Git Service.
To respond to the message,
tqchen commented on issue #5189:
URL: https://github.com/apache/incubator-tvm/issues/5189#issuecomment-617228247
https://github.com/apache/incubator-tvm/pull/5390
This is an automated message from the Apache Git Service.
To r
tqchen commented on issue #5390:
URL: https://github.com/apache/incubator-tvm/pull/5390#issuecomment-617228164
Thanks @areusch !
This is an automated message from the Apache Git Service.
To respond to the message, please log
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 be54c98 Fix test_ir_type. (#5390)
be54c9
gopinath-r commented on issue #5133:
URL: https://github.com/apache/incubator-tvm/issues/5133#issuecomment-617160891
@masahi I am trying to use tvm for the following model
[https://github.com/cogaplex-bts/bts/blob/master/pytorch/bts.py]
I am getting the following error while build
siju-samuel opened a new pull request #5394:
URL: https://github.com/apache/incubator-tvm/pull/5394
@anijain2305 @FrozenGene Please help to review.
I havent added any testcase beacause Im not able to simulate this from
testcases as there are no such ops in tf. This tflite ops will b
siju-samuel commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412128043
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(
masahi edited a comment on issue #5362:
URL: https://github.com/apache/incubator-tvm/pull/5362#issuecomment-617133013
Can we skip calibration (uncomment to encourage testing locally) and still
get meaningful output? I think it is unlikely we can update our CI for the sake
of this tutorial.
masahi commented on issue #5362:
URL: https://github.com/apache/incubator-tvm/pull/5362#issuecomment-617133013
Can we skip calibration and still get meaningful output? I think it is
unlikely we can update our CI for the sake of this tutorial.
--
masahi commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412113613
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(data,
siju-samuel commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412107805
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(
masahi commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412101164
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(data,
masahi commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412099376
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(data,
siju-samuel commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412097547
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(
siju-samuel commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412096961
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(
siju-samuel commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412096961
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(
siju-samuel commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412094229
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(
masahi edited a comment on issue #5363:
URL: https://github.com/apache/incubator-tvm/pull/5363#issuecomment-617110577
Thanks @anijain2305 @cbalint13 @tqchen
We should follow up to have a proper quantized winograd for ARM and possibly
for x86 too. I'm interested in this topic, but I
masahi commented on issue #5363:
URL: https://github.com/apache/incubator-tvm/pull/5363#issuecomment-617110577
Thanks @anijain2305 @cbalint13 @tqchen
This is an automated message from the Apache Git Service.
To respond to th
This is an automated email from the ASF dual-hosted git repository.
masahi 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 b39bd83 [Topi, ARM] Disbale Winograd for
This is an automated email from the ASF dual-hosted git repository.
masahi 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 5ce2c29 Add ability to have multiple cop
masahi commented on issue #5389:
URL: https://github.com/apache/incubator-tvm/pull/5389#issuecomment-617106831
Thanks @jwfromm
This is an automated message from the Apache Git Service.
To respond to the message, please log o
masahi commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412082233
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(data,
masahi commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412082233
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(data,
masahi commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412081790
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(data,
masahi commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412081790
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(data,
masahi commented on a change in pull request #5383:
URL: https://github.com/apache/incubator-tvm/pull/5383#discussion_r412082233
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -337,6 +337,55 @@ def _impl(inputs, input_types):
return _op.transform.repeat(data,
kevinthesun commented on issue #5373:
URL: https://github.com/apache/incubator-tvm/issues/5373#issuecomment-617007842
@tqchen Sorry I'm quite busy these days. Will work on it when I get time.
This is an automated message from
86 matches
Mail list logo