comaniac commented on issue #4468: [RFC] Data-flow Analysis Functionality on
TVM IR
URL: https://github.com/apache/incubator-tvm/issues/4468#issuecomment-562826046
@DKXXXL , thanks for the clarification and it seems fair enough to me :)
Then it seems like #4449, #3895 and this RFC
comaniac commented on a change in pull request #4465: [AutoTVM] Tune softmax
CUDA schedule
URL: https://github.com/apache/incubator-tvm/pull/4465#discussion_r355106974
##
File path: topi/python/topi/cuda/softmax.py
##
@@ -52,13 +60,22 @@ def schedule_softmax(outs):
DKXXXL commented on issue #4468: [RFC] Data-flow Analysis Functionality on TVM
IR
URL: https://github.com/apache/incubator-tvm/issues/4468#issuecomment-562806258
Hi @comaniac , Thanks for commenting. :)
Yes. This is a real problem happening in the industrial context. The
current
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/incubator-tvm-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 5d9b345 Build at Fri Dec 6
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-site.git
The following commit(s) were added to refs/heads/master by this push:
new 38b95a2 Add fb
38b95a2 is
alexgl-github opened a new pull request #4476: Implement 1d deconvolution
URL: https://github.com/apache/incubator-tvm/pull/4476
Thanks for contributing to TVM! Please refer to guideline
https://docs.tvm.ai/contribute/ for useful information and tips. After the pull
request is
junrushao1994 commented on issue #4471: [topi python API]
'bilinear_sample_nchw' is not supported in deformable_conv2d.py
URL: https://github.com/apache/incubator-tvm/issues/4471#issuecomment-562783833
Could you verify if it works? If so, we may close this issue for now.
apivovarov commented on a change in pull request #4472: Workaround to make
conv2d_transpose compilation for CUDA work
URL: https://github.com/apache/incubator-tvm/pull/4472#discussion_r355007762
##
File path: topi/python/topi/cuda/conv2d_transpose_nchw.py
##
@@ -186,7
apivovarov commented on a change in pull request #4472: Workaround to make
conv2d_transpose compilation for CUDA work
URL: https://github.com/apache/incubator-tvm/pull/4472#discussion_r354992237
##
File path: topi/python/topi/cuda/conv2d_transpose_nchw.py
##
@@ -186,7
apivovarov commented on a change in pull request #4472: Workaround to make
conv2d_transpose compilation for CUDA work
URL: https://github.com/apache/incubator-tvm/pull/4472#discussion_r354992237
##
File path: topi/python/topi/cuda/conv2d_transpose_nchw.py
##
@@ -186,7
apivovarov commented on a change in pull request #4472: Workaround to make
conv2d_transpose compilation for CUDA work
URL: https://github.com/apache/incubator-tvm/pull/4472#discussion_r354992237
##
File path: topi/python/topi/cuda/conv2d_transpose_nchw.py
##
@@ -186,7
apivovarov commented on a change in pull request #4472: Workaround to make
conv2d_transpose compilation for CUDA work
URL: https://github.com/apache/incubator-tvm/pull/4472#discussion_r354992237
##
File path: topi/python/topi/cuda/conv2d_transpose_nchw.py
##
@@ -186,7
apivovarov commented on issue #4447: [Relay][Frontend][TFlite] Add parses
support for UNPACK tflite operator
URL: https://github.com/apache/incubator-tvm/pull/4447#issuecomment-562693190
LGTM
@FrozenGene Can you have a look?
jwfromm commented on issue #4464: [RFC] Add TVMDSOOp to integrate any TVM
operator with TensorFlow
URL: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-562681167
The motivations of this RFC are extremely similar to those in
[pytorch-tvm](https://github.com/pytorch/tvm),
comaniac commented on issue #4468: [RFC] Data-flow Analysis Functionality on
TVM IR
URL: https://github.com/apache/incubator-tvm/issues/4468#issuecomment-562673761
Hey @DKXXXL, thanks for the example!
Just curious. Do you think the case of copy propagation caused dead code
happens in
tqchen commented on issue #4473: ci.tvm.ai is down
URL: https://github.com/apache/incubator-tvm/issues/4473#issuecomment-562625577
Thanks for reporting Double checked and seems the ci and docs are online
atm. Closing for now, please feel free open new threads
tqchen closed issue #4473: ci.tvm.ai is down
URL: https://github.com/apache/incubator-tvm/issues/4473
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
DKXXXL commented on issue #4468: [RFC] Data-flow Analysis Functionality on TVM
IR
URL: https://github.com/apache/incubator-tvm/issues/4468#issuecomment-562559678
Hi @junrushao1994 ,
an over-simplified example from the industrial context is the following:
```python
...
B0 =
anguoyang commented on issue #4262: [RELAY][Bug] 'name_hint' AttributeError
issue when covert tensorflow to TVM
URL: https://github.com/apache/incubator-tvm/issues/4262#issuecomment-562504897
@FinnWeng @Msabih I met the same problem, have you solved it? someone in TVM
forum said that it
Beya2019 opened a new pull request #4475: onnx frontend support layout choice
depend on hardware target support…
URL: https://github.com/apache/incubator-tvm/pull/4475
…ed layout with NCHW and NHWC
Thanks for contributing to TVM! Please refer to guideline
vinx13 merged pull request #4469: Fix typo in travserse
URL: https://github.com/apache/incubator-tvm/pull/4469
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from ba9d96b [relay][op] Add shape func to tile (#4441)
add 7cf1ead Fix typo in travserse (#4469)
No new
vinx13 commented on a change in pull request #4472: Workaround to make
conv2d_transpose compilation for CUDA work
URL: https://github.com/apache/incubator-tvm/pull/4472#discussion_r354714737
##
File path: topi/python/topi/cuda/conv2d_transpose_nchw.py
##
@@ -186,7 +186,9
vinx13 commented on a change in pull request #4472: Workaround to make
conv2d_transpose compilation for CUDA work
URL: https://github.com/apache/incubator-tvm/pull/4472#discussion_r354714737
##
File path: topi/python/topi/cuda/conv2d_transpose_nchw.py
##
@@ -186,7 +186,9
Beya2019 closed pull request #4474: onnx frontend support layout choice depend
on hardware target supported layout with NCHW and NHWC
URL: https://github.com/apache/incubator-tvm/pull/4474
This is an automated message from
25 matches
Mail list logo