marcelotrevisani opened a new issue #5981:
URL: https://github.com/apache/incubator-tvm/issues/5981
Just to let you know that I added TVM to the ``conda-forge``
So you will be able to install the tvm libs using conda such as:
``conda install -c conda-forge libtvm``
and the python
jwfromm commented on pull request #5975:
URL: https://github.com/apache/incubator-tvm/pull/5975#issuecomment-653053847
@merrymercy it's fairly quick, I commented out the run command due to
dependencies rather than the runtime. This tutorial requires tensorflow 2.2
(our servers currently
jcf94 commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r448939109
##
File path: python/tvm/ansor/compute_dag.py
##
@@ -0,0 +1,103 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
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 512ed39 [TOPI] Fix x86 conv2d template when tuning with unpacked
layout (#5938)
add 9c1e673 fix tvm
tqchen commented on pull request #5977:
URL: https://github.com/apache/incubator-tvm/pull/5977#issuecomment-653057178
Thanks @Leslie-Fang !
This is an automated message from the Apache Git Service.
To respond to the message,
tqchen merged pull request #5977:
URL: https://github.com/apache/incubator-tvm/pull/5977
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
jwfromm edited a comment on pull request #5975:
URL: https://github.com/apache/incubator-tvm/pull/5975#issuecomment-653053847
@merrymercy it's fairly quick, I commented out the run command due to
dependencies rather than the run time. This tutorial requires tensorflow 2.2
(our servers
jcf94 commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r448974042
##
File path: src/ansor/measure.h
##
@@ -0,0 +1,432 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor
kparzysz-quic opened a new pull request #5982:
URL: https://github.com/apache/incubator-tvm/pull/5982
The functions `CreateBufferPtr` and `CreateBufferVecPtr` do the exact same
thing, so there is no need for both of them to exist. The
latter is only used in place, which further suggests
areusch commented on a change in pull request #5960:
URL: https://github.com/apache/incubator-tvm/pull/5960#discussion_r449140041
##
File path: src/target/codegen.cc
##
@@ -47,7 +47,12 @@ runtime::Module Build(IRModule mod, const Target& target) {
.value()) {
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 6ce8a1c [Target] Migrate data structure
tqchen commented on pull request #5960:
URL: https://github.com/apache/incubator-tvm/pull/5960#issuecomment-653182013
Thanks @junrushao1994 @areusch
This is an automated message from the Apache Git Service.
To respond to
tqchen merged pull request #5960:
URL: https://github.com/apache/incubator-tvm/pull/5960
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
u99127 edited a comment on pull request #5975:
URL: https://github.com/apache/incubator-tvm/pull/5975#issuecomment-653161883
>
>
> @merrymercy it's fairly quick, I commented out the run command due to
dependencies rather than the run time. This tutorial requires tensorflow 2.2
u99127 commented on pull request #5975:
URL: https://github.com/apache/incubator-tvm/pull/5975#issuecomment-653161883
>
>
> @merrymercy it's fairly quick, I commented out the run command due to
dependencies rather than the run time. This tutorial requires tensorflow 2.2
(our
mbrookhart opened a new pull request #5983:
URL: https://github.com/apache/incubator-tvm/pull/5983
@icemelon9 @kevinthesun
FYI - I'm working on gradients for these ops, need to refactor the autodiff
testing a little bit to ignore these dynamic inputs, they shouldn't be
u99127 commented on pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#issuecomment-653135171
>
>
> @u99127 can you please take a look again?
LGTM.
This is an automated message from the
junrushao1994 commented on a change in pull request #5960:
URL: https://github.com/apache/incubator-tvm/pull/5960#discussion_r449148119
##
File path: tests/micro/test_runtime_micro_on_arm.py
##
@@ -33,7 +33,7 @@
# Ex : export
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 78a006c [LLVM] Remove redundant
tqchen merged pull request #5982:
URL: https://github.com/apache/incubator-tvm/pull/5982
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
jwfromm commented on a change in pull request #5975:
URL: https://github.com/apache/incubator-tvm/pull/5975#discussion_r449148996
##
File path: tutorials/frontend/deploy_sparse.py
##
@@ -0,0 +1,326 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
kparzysz-quic opened a new pull request #5984:
URL: https://github.com/apache/incubator-tvm/pull/5984
In LLVM 11+ the distinction between fixed and scalable vector types has
become more explicit. Before the introduction of scalable vector types
`VectorType::get(e,n)` created what is now a
anijain2305 commented on pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#issuecomment-653098040
@u99127 can you please take a look again?
This is an automated message from the Apache Git Service.
junrushao1994 commented on pull request #5960:
URL: https://github.com/apache/incubator-tvm/pull/5960#issuecomment-653105688
@areusch Hey Andrew, this PR changes the target definition of micro-dev from
`c -device=micro_dev` to `micro_dev`
anijain2305 commented on pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#issuecomment-653176255
@siju-samuel Please approve and merge if its looks good :)
This is an automated message from the
tqchen commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r449232301
##
File path: src/ansor/transform_step.cc
##
@@ -0,0 +1,241 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
tqchen commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r449232556
##
File path: src/ansor/transform_step.cc
##
@@ -0,0 +1,241 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
junrushao1994 commented on pull request #5976:
URL: https://github.com/apache/incubator-tvm/pull/5976#issuecomment-653201033
Hmmm just to confirm, do we really want to keep those "fake" operators in
the NNVM IR?
This is an
jroesch commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r449198373
##
File path: python/tvm/ansor/auto_schedule.py
##
@@ -0,0 +1,206 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
tqchen edited a comment on pull request #5985:
URL: https://github.com/apache/incubator-tvm/pull/5985#issuecomment-653209091
We cannot yet directly merge it(merging will result in ci outrage), because
of the CI error mentioned
tqchen commented on pull request #5985:
URL: https://github.com/apache/incubator-tvm/pull/5985#issuecomment-653209091
We cannot yet directly merge it, because of the CI error mentioned
(http://ci.tvm.ai:8080/job/temp-ci-docker-staging/job/ci-stage/39/execution/node/324/log/).
It won't be
tqchen commented on a change in pull request #5932:
URL: https://github.com/apache/incubator-tvm/pull/5932#discussion_r449303920
##
File path: src/parser/parser.cc
##
@@ -0,0 +1,1103 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor
kevinthesun commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r449235073
##
File path: python/tvm/ansor/auto_schedule.py
##
@@ -0,0 +1,206 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
comaniac commented on pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#issuecomment-653202171
Wait for #5985.
This is an automated message from the Apache Git Service.
To respond to the message,
comaniac commented on pull request #5985:
URL: https://github.com/apache/incubator-tvm/pull/5985#issuecomment-653212522
Sure no problem. Will also leave #5919 open during this time.
This is an automated message from the
comaniac closed pull request #5985:
URL: https://github.com/apache/incubator-tvm/pull/5985
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
tqchen commented on pull request #5985:
URL: https://github.com/apache/incubator-tvm/pull/5985#issuecomment-653212192
Let us close this for now, I will file another one when the issue get
resolved, sorry for the confusion. We will likely need to update tensorflow to
2.2 to resolve the
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 6ce8a1c [Target] Migrate data structure of TargetNode (#5960)
add a519292 [Tutorial] Demo showing how
tqchen commented on pull request #5975:
URL: https://github.com/apache/incubator-tvm/pull/5975#issuecomment-653225192
Thanks everyone, this is merged, will ping the thread again once we have TF
2.2 landed in the CI
This is
tqchen merged pull request #5975:
URL: https://github.com/apache/incubator-tvm/pull/5975
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
Leslie-Fang commented on issue #5978:
URL: https://github.com/apache/incubator-tvm/issues/5978#issuecomment-653250342
@FrozenGene Could you help to take a look of this issue:) Thanks
This is an automated message from the
comaniac opened a new pull request #5985:
URL: https://github.com/apache/incubator-tvm/pull/5985
After #5936, the latest docker image with DNNL is `tvmai/ci-cpu:0.63`.
cc @tqchen @zhiics
This is an automated message
comaniac commented on pull request #5985:
URL: https://github.com/apache/incubator-tvm/pull/5985#issuecomment-653210069
Ah...then would you suggest closing this PR first and you will file another
one after the issue has been resolved, or we just leave it here for now?
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 a519292 [Tutorial] Demo showing how to run a pruned 珞 model. (#5975)
add 5248c14 [LLVM]
tqchen merged pull request #5984:
URL: https://github.com/apache/incubator-tvm/pull/5984
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
tqchen commented on pull request #5984:
URL: https://github.com/apache/incubator-tvm/pull/5984#issuecomment-653266636
Thanks @kparzysz-quic @junrushao1994 !
This is an automated message from the Apache Git Service.
To
jcf94 commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r449339111
##
File path: src/ansor/utils.cc
##
@@ -0,0 +1,55 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor
jcf94 commented on pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#issuecomment-653291178
> Left a lot of feedback, overall would like to get some clarity in the docs
and comments, and think about reducing away some of the concepts to better map
to existing TVM
windclarion closed pull request #5987:
URL: https://github.com/apache/incubator-tvm/pull/5987
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r449345174
##
File path: python/tvm/runtime/graph_runtime_factory.py
##
@@ -0,0 +1,144 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+#
This is an automated email from the ASF dual-hosted git repository.
sijusamuel 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 575a383 [TFLite] QNN support for
siju-samuel commented on pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#issuecomment-653280854
Thanks @anijain2305 @u99127 @tqchen. This is now merged.
This is an automated message from the Apache
siju-samuel merged pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
samskalicky commented on pull request #5986:
URL: https://github.com/apache/incubator-tvm/pull/5986#issuecomment-653270573
@tqchen for review, @zhiics @trevor-m FYI
This is an automated message from the Apache Git Service.
tqchen commented on pull request #5986:
URL: https://github.com/apache/incubator-tvm/pull/5986#issuecomment-653288776
Thanks @samskalicky .
I agree that the destruction would be an issue here. The fix however, is a
bit adhoc. The root of problem is due to the fact of using a
tqchen commented on issue #5978:
URL: https://github.com/apache/incubator-tvm/issues/5978#issuecomment-653289235
Thanks for reporting the problem, the community uses https://discuss.tvm.ai/
for quick trouble shooting and discussions, please open a new thread there
tqchen commented on issue #5979:
URL: https://github.com/apache/incubator-tvm/issues/5979#issuecomment-653289036
Please open a new thread on https://discuss.tvm.ai/
This is an automated message from the Apache Git Service.
tqchen closed issue #5979:
URL: https://github.com/apache/incubator-tvm/issues/5979
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 go to
tqchen closed issue #5978:
URL: https://github.com/apache/incubator-tvm/issues/5978
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 go to
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r449346814
##
File path: python/tvm/rpc/client.py
##
@@ -160,7 +160,12 @@ def load_module(self, path):
m : Module
The remote module
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r449346502
##
File path: python/tvm/runtime/graph_runtime_factory.py
##
@@ -0,0 +1,144 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+#
windclarion opened a new pull request #5987:
URL: https://github.com/apache/incubator-tvm/pull/5987
src/target/target_id.cc ParseAttrsFromRawString L222:
if ((pos = FindUniqueSubstr(s, "=")) != -1)
require option contains only one '='
The CHECK code in FindUniqueSubstr will
samskalicky opened a new pull request #5986:
URL: https://github.com/apache/incubator-tvm/pull/5986
Ive been getting this issue when running tests, all pass, and then as the
process starts to exit fails with a core dump:
```
pure virtual method called
terminate called without an
icemelon9 commented on a change in pull request #5976:
URL: https://github.com/apache/incubator-tvm/pull/5976#discussion_r449321892
##
File path: python/tvm/relay/frontend/mxnet.py
##
@@ -903,6 +903,22 @@ def _mx_resize(inputs, attrs):
return _op.image.resize(inputs[0],
jcf94 commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r449339055
##
File path: python/tvm/ansor/serialization.py
##
@@ -0,0 +1,156 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
jcf94 commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r449338958
##
File path: python/tvm/ansor/serialization.py
##
@@ -0,0 +1,156 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r449345174
##
File path: python/tvm/runtime/graph_runtime_factory.py
##
@@ -0,0 +1,144 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+#
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r449346234
##
File path: python/tvm/runtime/graph_runtime_factory.py
##
@@ -0,0 +1,144 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+#
areusch commented on pull request #5921:
URL: https://github.com/apache/incubator-tvm/pull/5921#issuecomment-653318864
note: I couldn't get the llvm backend module to work on my mac. it could be
a mac issue, but building with c works fine, so perhaps it's a cflags problem?
areusch edited a comment on pull request #5921:
URL: https://github.com/apache/incubator-tvm/pull/5921#issuecomment-653318864
note: I couldn't get the llvm backend module for `bundle_deploy` to work on
my mac. it could be a mac issue, but building with c works fine, so perhaps
it's a
windclarion opened a new pull request #5988:
URL: https://github.com/apache/incubator-tvm/pull/5988
src/target/target_id.cc ParseAttrsFromRawString L222:
if ((pos = FindUniqueSubstr(s, "=")) != -1)
require option contains only one '='
The CHECK code in FindUniqueSubstr will
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r449346309
##
File path: python/tvm/runtime/graph_runtime_factory.py
##
@@ -0,0 +1,144 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+#
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r449346234
##
File path: python/tvm/runtime/graph_runtime_factory.py
##
@@ -0,0 +1,144 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+#
siju-samuel commented on a change in pull request #5988:
URL: https://github.com/apache/incubator-tvm/pull/5988#discussion_r449361801
##
File path: python/tvm/target/target.py
##
@@ -194,21 +194,22 @@ def arm_cpu(model='unknown', options=None):
Additional options
Leslie-Fang opened a new issue #5978:
URL: https://github.com/apache/incubator-tvm/issues/5978
I am trying to convert a resnet style model into TVM, but I got the error
message:
```
Traceback (most recent call last):
File "tensorflow_tvm.py", line 47, in
mod, params =
zhangzhen507 opened a new issue #5979:
URL: https://github.com/apache/incubator-tvm/issues/5979
I quantize DeepLabV3+ model from Tensorflow and meet the problem here.
The quantization pass has the following problem.
02-07-2020:01:42:42,719 INFO [_calibrate.py:99]
zhiics commented on a change in pull request #5962:
URL: https://github.com/apache/incubator-tvm/pull/5962#discussion_r448760203
##
File path: python/tvm/ansor/compute_dag.py
##
@@ -0,0 +1,141 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
kevinthesun commented on pull request #5938:
URL: https://github.com/apache/incubator-tvm/pull/5938#issuecomment-652801150
Thanks @merrymercy @junrushao1994 @tqchen
This is an automated message from the Apache Git Service.
giuseros commented on pull request #5980:
URL: https://github.com/apache/incubator-tvm/pull/5980#issuecomment-65255
cc @tqchen @anijain2305 @kparzysz-quic
This is an automated message from the Apache Git Service.
To
giuseros opened a new pull request #5980:
URL: https://github.com/apache/incubator-tvm/pull/5980
### RFC
This PR is based on the following RFC:
https://discuss.tvm.ai/t/rfc-using-arm-intrinsics-to-implement-fixed-point-multiplication-in-tvm/7150/6
### High level description of
80 matches
Mail list logo