tqchen commented on issue #6878:
URL: https://github.com/apache/incubator-tvm/issues/6878#issuecomment-723506521
I agree that for repr and str we should turn off the meta data since they
are not strictly required
This is an
junrushao1994 commented on pull request #6880:
URL: https://github.com/apache/incubator-tvm/pull/6880#issuecomment-723520652
I am not an expert in Sphinx. Would you like to take a look? @zhiics
@ZihengJiang
This is an
merrymercy commented on pull request #6882:
URL: https://github.com/apache/incubator-tvm/pull/6882#issuecomment-723535696
cc @jcf94 @FrozenGene @comaniac @tqchen @junrushao1994
This is an automated message from the Apache
merrymercy opened a new pull request #6880:
URL: https://github.com/apache/incubator-tvm/pull/6880
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
merrymercy merged pull request #6879:
URL: https://github.com/apache/incubator-tvm/pull/6879
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
This is an automated email from the ASF dual-hosted git repository.
lmzheng pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 5bce73c register auto-scheduler to more
vinx13 merged pull request #6714:
URL: https://github.com/apache/incubator-tvm/pull/6714
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
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 5e9ddeb More flexible conv2d_NCHWc_int8
merrymercy commented on pull request #6879:
URL: https://github.com/apache/incubator-tvm/pull/6879#issuecomment-723514958
@jcf94 @comaniac @FrozenGene
This is an automated message from the Apache Git Service.
To respond to
merrymercy edited a comment on pull request #6879:
URL: https://github.com/apache/incubator-tvm/pull/6879#issuecomment-723514958
@jcf94 @comaniac @FrozenGene @junrushao1994
This is an automated message from the Apache Git
merrymercy opened a new pull request #6879:
URL: https://github.com/apache/incubator-tvm/pull/6879
Register auto-scheduler as an implementation for conv2d, conv3d, and
depthwise conv2d in NHWC and NCHW layout.
This is an
merrymercy opened a new pull request #6881:
URL: https://github.com/apache/incubator-tvm/pull/6881
fix #6878
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub
merrymercy opened a new pull request #6882:
URL: https://github.com/apache/incubator-tvm/pull/6882
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
merrymercy commented on issue #6878:
URL: https://github.com/apache/incubator-tvm/issues/6878#issuecomment-723521610
Fixed by #6881
This is an automated message from the Apache Git Service.
To respond to the message, please
merrymercy opened a new pull request #6876:
URL: https://github.com/apache/incubator-tvm/pull/6876
This PR adds the winograd support for NHWC layout.
Now it is only enabled for GPU backend, but the CPU backend uses the same
compute declaration. I will enable it in later PRs.
merrymercy commented on a change in pull request #6842:
URL: https://github.com/apache/incubator-tvm/pull/6842#discussion_r519157759
##
File path: python/tvm/auto_scheduler/compute_dag.py
##
@@ -182,3 +187,11 @@ def hash_key(self):
str_key =
merrymercy commented on a change in pull request #6842:
URL: https://github.com/apache/incubator-tvm/pull/6842#discussion_r519157759
##
File path: python/tvm/auto_scheduler/compute_dag.py
##
@@ -182,3 +187,11 @@ def hash_key(self):
str_key =
merrymercy removed a comment on pull request #6876:
URL: https://github.com/apache/incubator-tvm/pull/6876#issuecomment-723422833
@jcf94 @FrozenGene @comaniac
This is an automated message from the Apache Git Service.
To
merrymercy removed a comment on pull request #6876:
URL: https://github.com/apache/incubator-tvm/pull/6876#issuecomment-723424316
replaced by #6877
This is an automated message from the Apache Git Service.
To respond to the
t-vi commented on pull request #6865:
URL: https://github.com/apache/incubator-tvm/pull/6865#issuecomment-723426822
Thank you @masahi and @jroesch and @areusch!
This is an automated message from the Apache Git Service.
To
cbalint13 commented on pull request #6714:
URL: https://github.com/apache/incubator-tvm/pull/6714#issuecomment-723428828
> @cbalint13 could you try restarting the CI?
@vinx13 , done, passed.
Thank You !
This is
merrymercy closed pull request #6876:
URL: https://github.com/apache/incubator-tvm/pull/6876
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
yigo3000 opened a new pull request #6875:
URL: https://github.com/apache/incubator-tvm/pull/6875
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
merrymercy commented on pull request #6876:
URL: https://github.com/apache/incubator-tvm/pull/6876#issuecomment-723422833
@jcf94 @FrozenGene @comaniac
This is an automated message from the Apache Git Service.
To respond to
merrymercy commented on pull request #6876:
URL: https://github.com/apache/incubator-tvm/pull/6876#issuecomment-723424316
replaced by #6877
This is an automated message from the Apache Git Service.
To respond to the message,
merrymercy opened a new pull request #6877:
URL: https://github.com/apache/incubator-tvm/pull/6877
This PR adds the Winograd support for NHWC layout.
Now it is only enabled for GPU backend, but the CPU backend uses the same
compute declaration. I will enable it in later PRs.
tqchen merged pull request #6873:
URL: https://github.com/apache/incubator-tvm/pull/6873
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
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/incubator-tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 4390010 [COMMUNITY] New committer --
trevor-m commented on a change in pull request #6872:
URL: https://github.com/apache/incubator-tvm/pull/6872#discussion_r519196129
##
File path: src/runtime/contrib/tensorrt/tensorrt_runtime.cc
##
@@ -106,9 +104,11 @@ class TensorRTRuntime : public JSONRuntimeBase {
#ifdef
This is an automated email from the ASF dual-hosted git repository.
lmzheng pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 12582fd [AutoScheduler] Make SearchTask
merrymercy merged pull request #6842:
URL: https://github.com/apache/incubator-tvm/pull/6842
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
comaniac commented on a change in pull request #6842:
URL: https://github.com/apache/incubator-tvm/pull/6842#discussion_r519199787
##
File path: python/tvm/auto_scheduler/compute_dag.py
##
@@ -182,3 +187,11 @@ def hash_key(self):
str_key =
comaniac commented on a change in pull request #6842:
URL: https://github.com/apache/incubator-tvm/pull/6842#discussion_r519199787
##
File path: python/tvm/auto_scheduler/compute_dag.py
##
@@ -182,3 +187,11 @@ def hash_key(self):
str_key =
comaniac commented on a change in pull request #6842:
URL: https://github.com/apache/incubator-tvm/pull/6842#discussion_r519199787
##
File path: python/tvm/auto_scheduler/compute_dag.py
##
@@ -182,3 +187,11 @@ def hash_key(self):
str_key =
merrymercy opened a new issue #6878:
URL: https://github.com/apache/incubator-tvm/issues/6878
Recently I found TVM will print meta when I do
```
print(tvm.lower(s, [A, B, C], simple_mode=True))
```
Here is an example output in the tutorial website
junrushao1994 commented on issue #6878:
URL: https://github.com/apache/incubator-tvm/issues/6878#issuecomment-723490419
You may slightly these lines:
https://github.com/apache/incubator-tvm/blob/main/python/tvm/ir/module.py#L253-L258,
adding `show_meta_data=False` to `self.astext`
junrushao1994 commented on issue #6878:
URL: https://github.com/apache/incubator-tvm/issues/6878#issuecomment-723490592
@jroesch shall we turn off the `show_meta_data` in `IRModule.__str__` and
`IRModule.__repr__`? If so, @merrymercy would you mind send a PR?
comaniac merged pull request #6872:
URL: https://github.com/apache/incubator-tvm/pull/6872
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
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/incubator-tvm.git
The following commit(s) were added to refs/heads/main by this push:
new c6cf58f [BYOC][TRT] Allocate GPU data
comaniac commented on pull request #6872:
URL: https://github.com/apache/incubator-tvm/pull/6872#issuecomment-723494809
Thanks @trevor-m @zhiics
This is an automated message from the Apache Git Service.
To respond to the
40 matches
Mail list logo