tqchen merged pull request #4744: Fix demo dockerfile build failed
URL: https://github.com/apache/incubator-tvm/pull/4744
This is an automated message from the Apache Git Service.
To respond to the message, please log on to
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from cf59b20 [REFACTOR] Establish tir (#4740)
add 992b5b5 Fix demo dockerfile build failed (#4744)
No new
tqchen commented on issue #4744: Fix demo dockerfile build failed
URL: https://github.com/apache/incubator-tvm/pull/4744#issuecomment-575973065
Thanks @pingsutw
This is an automated message from the Apache Git Service.
To
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 7e39201 Fix dense (#4728)
add cf59b20 [REFACTOR] Establish tir (#4740)
No new revisions were added by
pingsutw commented on issue #4744: Fix demo dockerfile build failed
URL: https://github.com/apache/incubator-tvm/pull/4744#issuecomment-575972880
Thanks @tqchen for the review
This is an automated message from the Apache Git
tqchen commented on issue #4740: [REFACTOR][IR] Establish tir namespace
URL: https://github.com/apache/incubator-tvm/pull/4740#issuecomment-575972930
Thanks @FrozenGene @Hzfengsy @ZihengJiang
This is an automated message
tqchen merged pull request #4740: [REFACTOR][IR] Establish tir namespace
URL: https://github.com/apache/incubator-tvm/pull/4740
This is an automated message from the Apache Git Service.
To respond to the message, please log
tqchen edited a comment on issue #4745: [Build][Bug] Updating CUDA from 10.0 to
10.1 resulted in a broken build even after running make clean
URL: https://github.com/apache/incubator-tvm/issues/4745#issuecomment-575972204
It might has something to do with stale cmake cache. So it may not
tqchen commented on issue #4745: [Build][Bug] Updating CUDA from 10.0 to 10.1
resulted in a broken build even after running make clean
URL: https://github.com/apache/incubator-tvm/issues/4745#issuecomment-575972204
It might has something to do with stale cmake cache. So it may not be a bug
slyubomirsky opened a new issue #4745: [Build][Bug] Updating CUDA from 10.0 to
10.1 resulted in a broken build even after running make clean
URL: https://github.com/apache/incubator-tvm/issues/4745
A bit of a strange case, but I wonder if there is a way to ensure that
running `make clean`
pingsutw opened a new pull request #4744: Fix demo dockerfile build failed
URL: https://github.com/apache/incubator-tvm/pull/4744
Fix dockerfile build failed since branch not found
Error message :
```
loning into '3rdparty/dmlc-core'...
Submodule path '3rdparty/dmlc-core':
Aeroxander opened a new issue #4743: [Relay][ONNX]KeyError: 'input.1' when
compiling from
URL: https://github.com/apache/incubator-tvm/issues/4743
So I raised this issue but haven't resolved it yet:
https://discuss.tvm.ai/t/keyerror-input-1-when-compiling-onnx-model/5333
I’m
FrozenGene commented on a change in pull request #4695:
[Relay][Frontend][TFlite] Add parser support for relational ops
URL: https://github.com/apache/incubator-tvm/pull/4695#discussion_r368262724
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -616,6 +621,36 @@
FrozenGene commented on a change in pull request #4695:
[Relay][Frontend][TFlite] Add parser support for relational ops
URL: https://github.com/apache/incubator-tvm/pull/4695#discussion_r368262762
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -722,6
FrozenGene commented on issue #4548: Windows support for autotvm - Do not merge
URL: https://github.com/apache/incubator-tvm/pull/4548#issuecomment-575960459
> I think that's a good idea @FrozenGene . Maybe starting with the CPP
server PR first, as it is more contained and less risky?
>
tqchen commented on issue #4742: [REFACTOR][CODEGEN] codegen->target,
build_module->driver
URL: https://github.com/apache/incubator-tvm/pull/4742#issuecomment-575957151
cc @zhiics @ajtulloch @yzhliu @merrymercy @hlu1 @ZihengJiang
tqchen opened a new pull request #4742: [REFACTOR][CODEGEN] codegen->target,
build_module->driver
URL: https://github.com/apache/incubator-tvm/pull/4742
This PR moves the codegen related code into the target folder,
as they are target specific functionalities.
We also adopt the
masahi opened a new pull request #4741: [Partitioning] Add test cases for fused
ops with manual annotation
URL: https://github.com/apache/incubator-tvm/pull/4741
* A custom annotator which detects conv + bias add + relu ops
* An example of applying FoldScaleAxis and FoldConstant to
tqchen edited a comment on issue #4740: [REFACTOR][IR] Establish tir namespace
URL: https://github.com/apache/incubator-tvm/pull/4740#issuecomment-575951640
cc @yzhliu @Hzfengsy @ZihengJiang @zhiics @FrozenGene @icemelon9 @merrymercy
tqchen edited a comment on issue #4740: [REFACTOR][IR] Establish tir namespace
URL: https://github.com/apache/incubator-tvm/pull/4740#issuecomment-575951640
cc @yzhliu @Hzfengsy @ZihengJiang @zhiics @FrozenGene @icemelon9
tqchen opened a new pull request #4740: [REFACTOR][IR] Establish tir namespace
URL: https://github.com/apache/incubator-tvm/pull/4740
TIR is the new namespace for low-level IR
for tensor-level optimizations and loop transformations.
This PR establishes the namespace and files.
jmorrill commented on issue #4548: Windows support for autotvm - Do not merge
URL: https://github.com/apache/incubator-tvm/pull/4548#issuecomment-575939098
I think that's a good idea @FrozenGene . Maybe starting with the CPP
server PR first, as it is more contained and less risky?
vinx13 edited a comment on issue #4738: Fix padding in pooling op
URL: https://github.com/apache/incubator-tvm/pull/4738#issuecomment-575936579
It's in `tests/python/relay/test_op_level2.py`, you can check the result of
infer_type in the test case
vinx13 commented on issue #4738: Fix padding in pooling op
URL: https://github.com/apache/incubator-tvm/pull/4738#issuecomment-575936579
It's in `tests/python/relay/test_op_level2.py`
This is an automated message from the
zhiics commented on issue #4258: [WIP][TVM] Bring Your Own Codegen to TVM
URL: https://github.com/apache/incubator-tvm/pull/4258#issuecomment-575925442
Let's close this since most of the work are merged. The annotation template
will be considered separately.
zhiics closed pull request #4258: [WIP][TVM] Bring Your Own Codegen to TVM
URL: https://github.com/apache/incubator-tvm/pull/4258
This is an automated message from the Apache Git Service.
To respond to the message, please
icemelon9 merged pull request #4693: [runtime][refactor] Unify vm and
interpreter objects
URL: https://github.com/apache/incubator-tvm/pull/4693
This is an automated message from the Apache Git Service.
To respond to the
icemelon9 merged pull request #4728: [Fix] Fix dense x86 schedule
URL: https://github.com/apache/incubator-tvm/pull/4728
This is an automated message from the Apache Git Service.
To respond to the message, please log on to
This is an automated email from the ASF dual-hosted git repository.
haichen 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 7e39201 Fix dense (#4728)
7e39201 is
icemelon9 commented on issue #4693: [runtime][refactor] Unify vm and
interpreter objects
URL: https://github.com/apache/incubator-tvm/pull/4693#issuecomment-575918719
Thanks @zhiics @tqchen @wweic @jroesch @MarisaKirisame . This is now merged.
This is an automated email from the ASF dual-hosted git repository.
haichen 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 acbf885 [runtime][refactor] Unify vm
anijain2305 commented on issue #4523: Optimization for subpixel layer on Tensor
core
URL: https://github.com/apache/incubator-tvm/issues/4523#issuecomment-575907399
https://docs.tvm.ai/dev/convert_layout.html
Please use the above tutorial to add support for nchw to nhwc layout.
kice commented on issue #4523: Optimization for subpixel layer on Tensor core
URL: https://github.com/apache/incubator-tvm/issues/4523#issuecomment-575894939
ConvertLayout only support NHWC(tf) -> NCHW(tvm), but I used mxnet to make
the layout conversion manually, and it turned out even
MarisaKirisame commented on issue #4693: [runtime][refactor] Unify vm and
interpreter objects
URL: https://github.com/apache/incubator-tvm/pull/4693#issuecomment-575880941
Thanks for the change. It now look right.
This is an
34 matches
Mail list logo
