DemonGiggle closed pull request #6392:
URL: https://github.com/apache/incubator-tvm/pull/6392
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
FrozenGene commented on a change in pull request #6391:
URL: https://github.com/apache/incubator-tvm/pull/6391#discussion_r483416557
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -657,9 +692,11 @@ def timed_func():
if error_no == 0:
try:
-
zxy844288792 commented on a change in pull request #6366:
URL: https://github.com/apache/incubator-tvm/pull/6366#discussion_r483378185
##
File path: python/tvm/contrib/target/onnx.py
##
@@ -349,13 +354,13 @@ def convert(cls, node_entry, model_container, node_dict):
n
jroesch commented on a change in pull request #6274:
URL: https://github.com/apache/incubator-tvm/pull/6274#discussion_r483345164
##
File path: include/tvm/ir/diagnostic.h
##
@@ -0,0 +1,254 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contri
vinx13 commented on pull request #6349:
URL: https://github.com/apache/incubator-tvm/pull/6349#issuecomment-686851043
You can add a check of cuda compute capability and skip the test if not
supported
This is an automated me
This is an automated email from the ASF dual-hosted git repository.
ziheng pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from af69e1c [CI][Contrib] Add Vitis-AI docker installation (#6342)
add a2db689 [METAL] Use CFBridgeRetain f
ZihengJiang merged pull request #6393:
URL: https://github.com/apache/incubator-tvm/pull/6393
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
zhiics commented on a change in pull request #6388:
URL: https://github.com/apache/incubator-tvm/pull/6388#discussion_r483309342
##
File path: tests/python/relay/test_any.py
##
@@ -893,6 +893,24 @@ def test_any_ndarray_size():
verify_any_ndarray_size((2, 2))
verify_an
zhiics commented on a change in pull request #6388:
URL: https://github.com/apache/incubator-tvm/pull/6388#discussion_r483309342
##
File path: tests/python/relay/test_any.py
##
@@ -893,6 +893,24 @@ def test_any_ndarray_size():
verify_any_ndarray_size((2, 2))
verify_an
zhiics commented on a change in pull request #6396:
URL: https://github.com/apache/incubator-tvm/pull/6396#discussion_r483304452
##
File path: src/relay/op/tensor/transform.h
##
@@ -180,6 +181,134 @@ static inline Array>
ConcatenateLayout(const Attrs& attrs,
return Array>{A
mbrookhart commented on a change in pull request #6396:
URL: https://github.com/apache/incubator-tvm/pull/6396#discussion_r483288604
##
File path: tests/python/relay/test_any.py
##
@@ -801,6 +801,23 @@ def test_any_ndarray_size():
verify_any_ndarray_size((2, 2))
verif
mbrookhart commented on a change in pull request #6388:
URL: https://github.com/apache/incubator-tvm/pull/6388#discussion_r483284293
##
File path: src/relay/op/tensor/transform.cc
##
@@ -3146,5 +3146,84 @@ RELAY_REGISTER_OP("matrix_set_diag")
.set_attr("FTVMCompute", Matri
tqchen commented on issue #6376:
URL: https://github.com/apache/incubator-tvm/issues/6376#issuecomment-686783855
Thanks @vathysjacob do you mind send a PR by adding the
`setPurgeableState:MTLPurgeableStateEmpty`?
It would also be interesting to ask if we should turn on the ARC, and w
zhiics commented on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-686779607
@trevor-m @masahi for the pass config, we may not be able to obtain at the
runtime though
This is an autom
jwfromm commented on a change in pull request #6351:
URL: https://github.com/apache/incubator-tvm/pull/6351#discussion_r483107517
##
File path: include/tvm/relay/transform.h
##
@@ -208,6 +208,17 @@ TVM_DLL Pass SimplifyInference();
*/
TVM_DLL Pass FastMath();
+/*!
+ * \bri
comaniac edited a comment on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-68670
For the rest 2 points.
2. Is that possible to move the pass before partitioning but after merge
compiler region (like `PruneTesnorRTCompilerRegion`)? After t
comaniac commented on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-68670
For the rest 2 points.
2. Is that possible to move the pass before partitioning but after merge
compiler region? After the merge compiler region pass you should get
trevor-m commented on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-686770757
> > ```
> > 1. Currently, I'm using environment variables to pass these from python
to the codegen in C++. I wonder if there is a better way to do this?
> > ```
>
masahi edited a comment on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-686768783
> 1. Currently, I'm using environment variables to pass these from
python to the codegen in C++. I wonder if there is a better way to do this?
How about us
masahi edited a comment on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-686768783
> 1. Currently, I'm using environment variables to pass these from
python to the codegen in C++. I wonder if there is a better way to do this?
How about us
masahi commented on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-686768783
> 1. Currently, I'm using environment variables to pass these from
python to the codegen in C++. I wonder if there is a better way to do this?
How about using Con
vathysjacob commented on issue #6376:
URL: https://github.com/apache/incubator-tvm/issues/6376#issuecomment-686766012
@tqchen - negative on #6393, memory usage continues to increase.
It looks like if manual reference counting is used, setPurgeableState needs
to be set to empty before
zhiics commented on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-686739951
Usually we need a separate PR to install the library/environment in the CI
first (TRT in this case) so that we can have better e2e tests.
tqchen commented on pull request #6297:
URL: https://github.com/apache/incubator-tvm/pull/6297#issuecomment-686729085
cc @jwfromm @mbrookhart @yzhliu
This is an automated message from the Apache Git Service.
To respond to th
zhiics commented on pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-686726858
cc @comaniac @mbaret @lhutton1 @masahi @leandron @mbrookhart
This is an automated message from the Apache
kevinthesun opened a new pull request #6396:
URL: https://github.com/apache/incubator-tvm/pull/6396
This PR fixes an issue that sometimes reshape with dynamic shape data but
constant attributes fusing with concatenate can generates ```Not all Vars are
passed in api_args``` error.
@z
trevor-m opened a new pull request #6395:
URL: https://github.com/apache/incubator-tvm/pull/6395
This PR adds support for partitioning, compiling, and running the TensorRT
BYOC target.
# Building
There are two new cmake flags:
* `USE_TENSORRT=ON/OFF`: enables TensorRT code
comaniac commented on a change in pull request #6391:
URL: https://github.com/apache/incubator-tvm/pull/6391#discussion_r483201157
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -657,9 +692,11 @@ def timed_func():
if error_no == 0:
try:
-
FrozenGene commented on a change in pull request #6391:
URL: https://github.com/apache/incubator-tvm/pull/6391#discussion_r483200130
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -657,9 +692,11 @@ def timed_func():
if error_no == 0:
try:
-
FrozenGene commented on a change in pull request #6391:
URL: https://github.com/apache/incubator-tvm/pull/6391#discussion_r483200130
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -657,9 +692,11 @@ def timed_func():
if error_no == 0:
try:
-
tkonolige commented on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686681682
I think this change is fine. The real problem seems to be a conflation of
targets and devices in a lot of the tests. I think we might also have to
improve `tvm.runtime.e
tqchen commented on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-68259
That is also why in the original test cases the LLVM arm code generator
tests are done in a different way(always enabled because llvm covers these
cases), and we don't run
tqchen edited a comment on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686664859
It is a bit confusing to do `runtime.enabled("llvm -mtriple=nonexistant")`
test.
Because `llvm -mtriple=nonexistant` is a target(whether we can generate code
tqchen commented on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686664859
It is a bit confusing to do `runtime.enabled("llvm -mtriple=nonexistant")`
test.
Because `llvm -mtriple=nonexistant` is a target(whether we can generate code
for th
nhynes commented on issue #6389:
URL: https://github.com/apache/incubator-tvm/issues/6389#issuecomment-686658268
Nice benchmarks. The latency you're seeing is almost surely due to paging.
My guess is that about 12 M are being used for your NN and other housekeeping
structures. SGXv1 EPC on
tkonolige commented on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686656965
This test fails: `TVM_TEST_TARGETS="llvm -mtriple=nonexistant" python3 -m
pytest tests/python/relay/test_op_level2.py`.
Many of the tests used to use `tvm.runtime.
mbrookhart commented on pull request #6351:
URL: https://github.com/apache/incubator-tvm/pull/6351#issuecomment-686653692
Thanks to @tmoreau89 for testing some custom models against this branch and
finding a regression. Any one else using ONNX, I'd really appreciate it if you
could do the
electriclilies commented on a change in pull request #6353:
URL: https://github.com/apache/incubator-tvm/pull/6353#discussion_r483153389
##
File path: python/tvm/relay/op/dyn/nn/_nn.py
##
@@ -47,12 +61,12 @@ def compute_upsampling(attrs, inputs, out_dtype):
# upsampling
@sc
tmoreau89 commented on pull request #6342:
URL: https://github.com/apache/incubator-tvm/pull/6342#issuecomment-686650367
Thanks @anilmartha @jtuyls @comaniac @leandron @tqchen the PR has been
merged. @leandron and @jtuyls can work together on follow-up improvements as
discussed.
comaniac commented on a change in pull request #6391:
URL: https://github.com/apache/incubator-tvm/pull/6391#discussion_r483151525
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -657,9 +692,11 @@ def timed_func():
if error_no == 0:
try:
-
This is an automated email from the ASF dual-hosted git repository.
moreau pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 17d39fb [Relay] Fix Type Arguments not Attached (#6385)
add af69e1c [CI][Contrib] Add Vitis-AI docker i
tqchen edited a comment on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686647893
`opencl -device=xyz` will fail on my local mac when running tests.
This happens when I directly run `python
tests/python/integration/test_ewise.py`
The
tmoreau89 merged pull request #6342:
URL: https://github.com/apache/incubator-tvm/pull/6342
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 t
tqchen edited a comment on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686647893
`opencl -device=xyz` will fail on my local mac when running tests.
This happens when I directly run `python
tests/python/integration/test_ewise.py`
The
tqchen commented on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686647893
`opencl -device=xyz` will fail on my local mac when running tests.
There is a difference between whether a target is enabled, versus whether a
runtime is available.
tqchen closed issue #2562:
URL: https://github.com/apache/incubator-tvm/issues/2562
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 commented on issue #2562:
URL: https://github.com/apache/incubator-tvm/issues/2562#issuecomment-686646105
closing for now due to inactive status, let us open new thread for new TODOs
of gradients
This is an automated
tkonolige edited a comment on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686642546
Which target strings is this failing with?
It seems like we want to test if the full target string is enabled with
`tvm.runtime.enabled`. For example `llvm
zhiics commented on pull request #6316:
URL: https://github.com/apache/incubator-tvm/pull/6316#issuecomment-686643391
@masahi @electriclilies could you take another look and approve/comment?
This is an automated message from
tkonolige commented on pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394#issuecomment-686642546
Which target strings is this failing with?
It seems like we want to test if the full target string is enabled with
`tvm.runtime.enabled`. For example `tvm.runtime.
zhiics commented on pull request #6316:
URL: https://github.com/apache/incubator-tvm/pull/6316#issuecomment-686642705
@mbrookhart no problem
BTW, I would suggest moving the compute to topi and make dynamic version
there in the next PR. Do we need to change the topi strided_slice defi
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 5262765 [Bugfix][Printer] Avoid adding annotation twice for
ConstantNode (#6364)
add 17d39fb [Relay] F
tqchen commented on pull request #6385:
URL: https://github.com/apache/incubator-tvm/pull/6385#issuecomment-686641970
THanks @MarisaKirisame @junrushao1994 @hypercubestart !
This is an automated message from the Apache Git Se
tqchen merged pull request #6385:
URL: https://github.com/apache/incubator-tvm/pull/6385
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 g
tqchen commented on issue #6376:
URL: https://github.com/apache/incubator-tvm/issues/6376#issuecomment-686641648
Thanks @vathysjacob ! please see if
https://github.com/apache/incubator-tvm/pull/6393 helps
This is an automate
mbrookhart commented on pull request #6316:
URL: https://github.com/apache/incubator-tvm/pull/6316#issuecomment-686640006
> @mbrookhart #6337 has been merged. You can try to enable the GPU tests now
I think I'd like to do it as a separate PR after we get this merged, I don't
want to
mbrookhart commented on pull request #6337:
URL: https://github.com/apache/incubator-tvm/pull/6337#issuecomment-686635409
Sorry for my delay! I've been out the last few days moving. Anyway, looking
over what was changed since my last review, I'm happy to give it a post-merge
approval, look
zhiics commented on a change in pull request #6353:
URL: https://github.com/apache/incubator-tvm/pull/6353#discussion_r483136682
##
File path: tests/python/relay/dyn/test_dynamic_op_level2.py
##
@@ -52,30 +52,84 @@ def verify_upsampling(dshape, scale_h, scale_w, layout,
method
zhiics commented on a change in pull request #6353:
URL: https://github.com/apache/incubator-tvm/pull/6353#discussion_r483136198
##
File path: tests/python/relay/dyn/test_dynamic_op_level2.py
##
@@ -52,30 +52,84 @@ def verify_upsampling(dshape, scale_h, scale_w, layout,
method
tqchen opened a new pull request #6394:
URL: https://github.com/apache/incubator-tvm/pull/6394
The previous testing.py causes problem of not being able to run the test
with the default set of targets.
We might also want to update the code further to memoize the list of targets
in th
tqchen opened a new pull request #6393:
URL: https://github.com/apache/incubator-tvm/pull/6393
cc @ajtulloch
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and us
FrozenGene commented on a change in pull request #6391:
URL: https://github.com/apache/incubator-tvm/pull/6391#discussion_r483128177
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -657,9 +692,11 @@ def timed_func():
if error_no == 0:
try:
-
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 1224d56 [RELAY][VM] Enable heterogeneous execution for Relay VM
(#6337)
add 5262765 [Bugfix][Printer] Av
zhiics commented on pull request #6364:
URL: https://github.com/apache/incubator-tvm/pull/6364#issuecomment-686624197
Thanks @yzhliu @junrushao1994
This is an automated message from the Apache Git Service.
To respond to the
zhiics merged pull request #6364:
URL: https://github.com/apache/incubator-tvm/pull/6364
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 g
icemelon9 commented on pull request #6337:
URL: https://github.com/apache/incubator-tvm/pull/6337#issuecomment-686618741
Thanks @zhiics @mbrookhart @leandron @jwfromm
This is an automated message from the Apache Git Service.
icemelon9 merged pull request #6337:
URL: https://github.com/apache/incubator-tvm/pull/6337
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 t
This is an automated email from the ASF dual-hosted git repository.
haichen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 12d66d4 [DOCS] Fix the docker binary cache location (#6390)
add 1224d56 [RELAY][VM] Enable heterogeneo
tqchen commented on issue #6389:
URL: https://github.com/apache/incubator-tvm/issues/6389#issuecomment-686614498
cc @nhynes @jroesch
This is an automated message from the Apache Git Service.
To respond to the message, please
tqchen merged pull request #6390:
URL: https://github.com/apache/incubator-tvm/pull/6390
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 g
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 237b4c1 [TFLite] Support for 'SAME' Padding option for TRANSPOSE_CONV
operator of TFLite. (#6381)
add 1
tqchen merged pull request #6381:
URL: https://github.com/apache/incubator-tvm/pull/6381
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 g
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 6770d28 [Frontend][TensorFlow] Improve TensorFlow control flow nodes
ordering (#6387)
add 237b4c1 [TFL
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 19de625 Make docs build again when not everything is enabled (#6386)
add 6770d28 [Frontend][TensorFlow] I
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 19de625 Make docs build again when not everything is enabled (#6386)
add 6770d28 [Frontend][TensorFlow] I
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 19de625 Make docs build again when not everything is enabled (#6386)
add 6770d28 [Frontend][TensorFlow] I
zhiics merged pull request #6387:
URL: https://github.com/apache/incubator-tvm/pull/6387
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 g
comaniac commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483105275
##
File path: tests/python/contrib/test_vitis_ai/test_vitis_ai_codegen.py
##
@@ -196,8 +213,13 @@ def expected():
if __name__ == "__main__":
-
comaniac commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483103694
##
File path: docs/deploy/vitis_ai.rst
##
@@ -285,8 +305,10 @@ platform. The following development boards can be used
out-of-the-box:
Edge hard
comaniac commented on a change in pull request #6391:
URL: https://github.com/apache/incubator-tvm/pull/6391#discussion_r483101547
##
File path: python/tvm/auto_scheduler/measure.py
##
@@ -657,9 +692,11 @@ def timed_func():
if error_no == 0:
try:
-
jtuyls commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483100207
##
File path: tests/python/contrib/test_vitis_ai/test_vitis_ai_codegen.py
##
@@ -196,8 +213,13 @@ def expected():
if __name__ == "__main__":
-
leandron commented on a change in pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r483100119
##
File path: python/tvm/driver/tvmc/compiler.py
##
@@ -0,0 +1,407 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more cont
comaniac commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483098980
##
File path: tests/python/contrib/test_vitis_ai/test_vitis_ai_codegen.py
##
@@ -196,8 +213,13 @@ def expected():
if __name__ == "__main__":
-
jtuyls commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483097224
##
File path: docs/deploy/vitis_ai.rst
##
@@ -285,8 +305,10 @@ platform. The following development boards can be used
out-of-the-box:
Edge hardwa
comaniac commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483095412
##
File path: docs/deploy/vitis_ai.rst
##
@@ -285,8 +305,10 @@ platform. The following development boards can be used
out-of-the-box:
Edge hard
jtuyls commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483088576
##
File path: docs/deploy/vitis_ai.rst
##
@@ -285,8 +305,10 @@ platform. The following development boards can be used
out-of-the-box:
Edge hardwa
jtuyls commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483087380
##
File path: tests/python/contrib/test_vitis_ai/test_vitis_ai_runtime.py
##
@@ -101,4 +103,7 @@ def test_extern_vai_resnet18():
check_result(mo
jtuyls commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483087232
##
File path: tests/python/contrib/test_vitis_ai/test_vitis_ai_codegen.py
##
@@ -196,8 +213,13 @@ def expected():
if __name__ == "__main__":
-
comaniac commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483073842
##
File path: docs/deploy/vitis_ai.rst
##
@@ -285,8 +305,10 @@ platform. The following development boards can be used
out-of-the-box:
Edge hard
mbaret commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r483069009
##
File path: tests/python/contrib/test_vitis_ai_codegen.py
##
@@ -0,0 +1,203 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or
mbrookhart commented on a change in pull request #6353:
URL: https://github.com/apache/incubator-tvm/pull/6353#discussion_r483021604
##
File path: python/tvm/relay/op/dyn/nn/_nn.py
##
@@ -47,12 +61,12 @@ def compute_upsampling(attrs, inputs, out_dtype):
# upsampling
@script
leandron commented on a change in pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r482965966
##
File path: python/tvm/driver/tvmc/common.py
##
@@ -17,6 +17,74 @@
"""
Common utility functions shared by TVMC modules.
"""
+import argparse
+
xutianming commented on pull request #6380:
URL: https://github.com/apache/incubator-tvm/pull/6380#issuecomment-686446990
@icemelon9 Could you please review this PR ?
This is an automated message from the Apache Git Service.
anilmartha commented on a change in pull request #6343:
URL: https://github.com/apache/incubator-tvm/pull/6343#discussion_r482920683
##
File path: tests/python/contrib/test_vitis_ai_runtime.py
##
@@ -0,0 +1,104 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+#
masahi commented on a change in pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r482881831
##
File path: python/tvm/driver/tvmc/compiler.py
##
@@ -0,0 +1,407 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contri
leandron commented on a change in pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r482858084
##
File path: python/tvm/driver/tvmc/compiler.py
##
@@ -0,0 +1,407 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more cont
leandron commented on a change in pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r482858084
##
File path: python/tvm/driver/tvmc/compiler.py
##
@@ -0,0 +1,407 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more cont
leandron commented on a change in pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r482832429
##
File path: python/tvm/driver/tvmc/compiler.py
##
@@ -0,0 +1,305 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more cont
DemonGiggle opened a new pull request #6392:
URL: https://github.com/apache/incubator-tvm/pull/6392
In these places, the `args` had been decayed as lvalue. No need to
preserve its value category.
This is an automated m
xutianming removed a comment on pull request #6380:
URL: https://github.com/apache/incubator-tvm/pull/6380#issuecomment-686344347
please check / test / retest this
This is an automated message from the Apache Git Service.
To
1 - 100 of 107 matches
Mail list logo