kevinthesun commented on a change in pull request #4303: [TOPI][Relay][OP] Add
a strided_set operation.
URL: https://github.com/apache/incubator-tvm/pull/4303#discussion_r349860433
##
File path: python/tvm/relay/op/transform.py
##
@@ -631,6 +631,36 @@ def
kevinthesun commented on a change in pull request #4384: [ARM CPU] Fix infer
shape error of depthwise
URL: https://github.com/apache/incubator-tvm/pull/4384#discussion_r349860144
##
File path: python/tvm/relay/op/nn/_nn.py
##
@@ -163,10 +163,17 @@ def
kevinthesun merged pull request #4399: [Relay][Legalize] Legalize
conv2d_transpose for NHWC
URL: https://github.com/apache/incubator-tvm/pull/4399
This is an automated message from the Apache Git Service.
To respond to the
kevinthesun commented on issue #4399: [Relay][Legalize] Legalize
conv2d_transpose for NHWC
URL: https://github.com/apache/incubator-tvm/pull/4399#issuecomment-557770321
Thanks @apivovarov
This is an automated message from
This is an automated email from the ASF dual-hosted git repository.
kevinthesun pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 87bd799 [RUNTIME] Move module export to the function level. (#4405)
add 9049d66 [Relay][Legalize]
yzhliu opened a new issue #4406: [RFC] Apache TVM 0.6.0 Release Candidate 0
URL: https://github.com/apache/incubator-tvm/issues/4406
Dear Community,
This is an RFC for verifying whether v0.6.0rc0 is good to go. The release
candidate (release note, artifact and source code) can be
optima2005 commented on a change in pull request #4400: implement conv3d op
URL: https://github.com/apache/incubator-tvm/pull/4400#discussion_r349859513
##
File path: python/tvm/contrib/cudnn.py
##
@@ -384,3 +384,288 @@ def conv2d_forward(x,
ins[0],
optima2005 commented on a change in pull request #4400: implement conv3d op
URL: https://github.com/apache/incubator-tvm/pull/4400#discussion_r349859531
##
File path: python/tvm/contrib/cudnn.py
##
@@ -384,3 +384,288 @@ def conv2d_forward(x,
ins[0],
optima2005 commented on a change in pull request #4400: implement conv3d op
URL: https://github.com/apache/incubator-tvm/pull/4400#discussion_r349859526
##
File path: python/tvm/contrib/cudnn.py
##
@@ -384,3 +384,288 @@ def conv2d_forward(x,
ins[0],
kevinthesun commented on issue #4324: [Relay] Use opaque for where op
URL: https://github.com/apache/incubator-tvm/pull/4324#issuecomment-557768279
@icemelon9 Looks like the performance gap is not huge for cpu. We can keep
the current fusion pattern then.
This is an automated email from the ASF dual-hosted git repository.
liuyizhi pushed a change to tag 0.6.0.rc0
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
at 452fa4b (commit)
No new revisions were added by this update.
This is an automated email from the ASF dual-hosted git repository.
liuyizhi pushed a change to branch v0.6.0
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
omit 7429997 [LICENSE] add 3rdparty licenses (#4402)
omit 0f4b32f Added tflite frontend support for
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch v0.6.0
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 030a163 update_document_after_repository_renamed (#4398)
add 70017ef [Golang][Doc] improve the samples
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 e081051 [TVM][RUNTIME] A minimum example to generate external library
wrappers for DSOModule (#4280)
tqchen merged pull request #4405: [RUNTIME] Move module export to the function
level.
URL: https://github.com/apache/incubator-tvm/pull/4405
This is an automated message from the Apache Git Service.
To respond to the
tmoreau89 commented on issue #4318: [Relay][TOPI]Fix meaning of
conv2d_transpose output_padding parameter
URL: https://github.com/apache/incubator-tvm/pull/4318#issuecomment-557766083
@abergeron: I have good new and bad news. The *good news* is that I was able
to find the root cause of
masahi commented on issue #4400: implement conv3d op
URL: https://github.com/apache/incubator-tvm/pull/4400#issuecomment-557763063
@optima2005 can you add test cases to topi/tests/python too?
This is an automated message from
tqchen commented on issue #4405: [RUNTIME] Move module export to the function
level.
URL: https://github.com/apache/incubator-tvm/pull/4405#issuecomment-557762557
cc @yzhliu
This is an automated message from the Apache Git
masahi commented on issue #4400: implement conv3d op
URL: https://github.com/apache/incubator-tvm/pull/4400#issuecomment-557762187
@optima2005 thank you very much for working on this. Can we use cuDNN's ND
API like cudnnSetConvolutionNdDescriptor for 2D convolution? It would be great
if
masahi commented on a change in pull request #4400: implement conv3d op
URL: https://github.com/apache/incubator-tvm/pull/4400#discussion_r349855690
##
File path: src/relay/op/nn/convolution.cc
##
@@ -107,6 +107,63 @@ with the layer input to produce a tensor of outputs.
masahi commented on a change in pull request #4400: implement conv3d op
URL: https://github.com/apache/incubator-tvm/pull/4400#discussion_r349855307
##
File path: python/tvm/contrib/cudnn.py
##
@@ -384,3 +384,288 @@ def conv2d_forward(x,
ins[0],
masahi commented on a change in pull request #4400: implement conv3d op
URL: https://github.com/apache/incubator-tvm/pull/4400#discussion_r349855314
##
File path: python/tvm/contrib/cudnn.py
##
@@ -384,3 +384,288 @@ def conv2d_forward(x,
ins[0],
broune commented on a change in pull request #4370: [WIP] Relay visualization:
exporter + visualizer
URL: https://github.com/apache/incubator-tvm/pull/4370#discussion_r349854956
##
File path: python/tvm/relay/analysis.py
##
@@ -408,3 +411,116 @@ def
yangjunpro commented on issue #2954: [RFC][AUTOTVM] Auto-Schedule from Compute
Declaration
URL: https://github.com/apache/incubator-tvm/issues/2954#issuecomment-557759402
> Hi @yangjunpro @hello-hzb ,
> This project has been suspended for several months. I won't continue my
work on the
tqchen edited a comment on issue #4304: [RFC] Benchmark Performance Log Format
WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557753424
To address @u99127 's concern, we could add an optional runtime_raw field.
Note we may not be able to get accurate measurement
tqchen edited a comment on issue #4304: [RFC] Benchmark Performance Log Format
WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557753424
To address @u99127 's concern, we could add an optional runtime_raw field.
Note we may not necessarily be able to get accurate
tqchen commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557753424
To address @u99127 's concern, we could add an optional runtime_raw field.
Note we may not necessarily be able to get accurate
tqchen opened a new pull request #4405: [RUNTIME] Move module export to the
function level.
URL: https://github.com/apache/incubator-tvm/pull/4405
cc @zhiics @comaniac
This is an automated message from the Apache Git
tqchen edited a comment on issue #4280: [TVM][RUNTIME] A minimum example to
generate external library wrappers for DSOModule
URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-557751864
@zhiics @comaniac please followup to fix the windows build error here
tqchen commented on issue #4280: [TVM][RUNTIME] A minimum example to generate
external library wrappers for DSOModule
URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-557751864
@zhiics @comaniac please followup to fix the windows build error here
broune commented on a change in pull request #4404: [AutoTVM] select model with
the most tuned schedules
URL: https://github.com/apache/incubator-tvm/pull/4404#discussion_r349849273
##
File path: python/tvm/autotvm/tophub.py
##
@@ -218,12 +218,14 @@ def
u99127 commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557749626
@tmoreau89 - I lean more towards storing the list of raw measurements.
tmoreau89 commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557748992
@u99127 do you lean more towards storing the list of measurements (e.g. over
10 runs) and letting the user implement their
u99127 commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557748479
Thanks @tqchen , Ok, now the term "engine" makes sense.
My experience has been different. Some prefer median over mean, others
tqchen commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557744542
re @u99127 's comment about raw statistics, given that some executions have
to be run over multiple iterations to get a meaningful
u99127 commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349843771
##
File path: python/tvm/micro/device/arm/stm32f746xx.py
##
@@ -0,0 +1,123 @@
+# Licensed to
tqchen commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557743387
After looking at the schema for a bit. I feel that it would be helpful to
categorize things into two categories:
- timestamp,
u99127 commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557742808
To pick up on a couple of topics from the Pull Request.
1. I've found that keeping the raw data allows one to process it in
tqchen commented on issue #4366: [DOCS] add benchmark log format doc
URL: https://github.com/apache/incubator-tvm/pull/4366#issuecomment-557742019
@u99127 would be great if you can bring the proposed changes to the RFC
discussion. Given that this is a proposal for standard among the
u99127 commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349841762
##
File path: python/tvm/micro/device/arm/stm32f746xx.py
##
@@ -0,0 +1,123 @@
+# Licensed to
u99127 commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349841385
##
File path: python/tvm/micro/device/arm/stm32f746xx.py
##
@@ -0,0 +1,123 @@
+# Licensed to
weberlo commented on issue #4274: [µTVM] Enable AutoTVM for ARM STM32F746XX
Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#issuecomment-557740279
> Now, why is this important ? In this world there are multiple
implementations with Cortex-M7 with an FP5-SP-D16 FPU init, but
niconiconi closed issue #4403: [RFC][Cryptography] Modernize the cryptography
implementation
URL: https://github.com/apache/incubator-tvm/issues/4403
This is an automated message from the Apache Git Service.
To respond to
niconiconi commented on issue #4403: [RFC][Cryptography] Modernize the
cryptography implementation
URL: https://github.com/apache/incubator-tvm/issues/4403#issuecomment-557739982
> Interesting, cc @nhynes regarding rust interface.
niconiconi opened a new issue #4403: [RFC][Cryptography] Modernize the
cryptography implementation
URL: https://github.com/apache/incubator-tvm/issues/4403
Significant progress has been made during recent years due to the
development of blockchain. However, these cryptography protocols
niconiconi removed a comment on issue #4403: [RFC][Cryptography] Modernize the
cryptography implementation
URL: https://github.com/apache/incubator-tvm/issues/4403#issuecomment-557739982
> Interesting, cc @nhynes regarding rust interface.
nhynes edited a comment on issue #4403: [RFC][Cryptography] Modernize the
cryptography implementation
URL: https://github.com/apache/incubator-tvm/issues/4403#issuecomment-557739011
> rust interface
The rust interface is currently only that of a TVM runtime, but that's
sufficient
weberlo commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349839684
##
File path: python/tvm/micro/device/arm/stm32f746xx.py
##
@@ -0,0 +1,123 @@
+# Licensed to
weberlo commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349838632
##
File path: python/tvm/micro/base.py
##
@@ -14,129 +14,157 @@
# KIND, either express or
nhynes commented on issue #4403: [RFC][Cryptography] Modernize the cryptography
implementation
URL: https://github.com/apache/incubator-tvm/issues/4403#issuecomment-557739011
> rust interface
The rust interface is currently only that of a TVM runtime, but that's
sufficient since
weberlo commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349839226
##
File path: python/tvm/micro/device/arm/stm32f746xx.py
##
@@ -0,0 +1,123 @@
+# Licensed to
weberlo commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349839885
##
File path: src/runtime/micro/micro_session.h
##
@@ -174,29 +204,24 @@ class MicroSession :
u99127 commented on a change in pull request #4366: [DOCS] add benchmark log
format doc
URL: https://github.com/apache/incubator-tvm/pull/4366#discussion_r349835991
##
File path: docs/dev/benchmark.rst
##
@@ -0,0 +1,123 @@
+.. Licensed to the Apache Software Foundation
u99127 commented on a change in pull request #4366: [DOCS] add benchmark log
format doc
URL: https://github.com/apache/incubator-tvm/pull/4366#discussion_r349835941
##
File path: docs/dev/benchmark.rst
##
@@ -0,0 +1,123 @@
+.. Licensed to the Apache Software Foundation
u99127 commented on a change in pull request #4366: [DOCS] add benchmark log
format doc
URL: https://github.com/apache/incubator-tvm/pull/4366#discussion_r349834678
##
File path: docs/dev/benchmark.rst
##
@@ -0,0 +1,123 @@
+.. Licensed to the Apache Software Foundation
u99127 commented on a change in pull request #4366: [DOCS] add benchmark log
format doc
URL: https://github.com/apache/incubator-tvm/pull/4366#discussion_r349836030
##
File path: docs/dev/benchmark.rst
##
@@ -0,0 +1,123 @@
+.. Licensed to the Apache Software Foundation
masahi commented on issue #4403: [RFC][Cryptography] Modernize the cryptography
implementation
URL: https://github.com/apache/incubator-tvm/issues/4403#issuecomment-557733313
Interesting, cc @nhynes regarding rust interface.
apivovarov commented on a change in pull request #4399: [Relay][Legalize]
Legalize conv2d_transpose for NHWC
URL: https://github.com/apache/incubator-tvm/pull/4399#discussion_r349834656
##
File path: topi/python/topi/nn/conv2d_transpose.py
##
@@ -102,3 +103,61 @@ def
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 7429997 [LICENSE] add 3rdparty licenses (#4402)
add e081051 [TVM][RUNTIME] A minimum example to
tqchen merged pull request #4280: [TVM][RUNTIME] A minimum example to generate
external library wrappers for DSOModule
URL: https://github.com/apache/incubator-tvm/pull/4280
This is an automated message from the Apache Git
anijain2305 commented on a change in pull request #4399: [Relay][Legalize]
Legalize conv2d_transpose for NHWC
URL: https://github.com/apache/incubator-tvm/pull/4399#discussion_r349829981
##
File path: topi/python/topi/nn/conv2d_transpose.py
##
@@ -102,3 +103,61 @@ def
icemelon9 commented on issue #4324: [Relay] Use opaque for where op
URL: https://github.com/apache/incubator-tvm/pull/4324#issuecomment-557727463
@tqchen After some benchmark, I do see there's slightly improvement on the
CPU instances. On C5.9xl, with where being opaque, the latency of
tmoreau89 commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557726382
@tqchen `docker_tag` is under metadata; therefore it's mostly seen as
optional (and is here for example purposes)
Indeed
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 0f4b32f Added tflite frontend support for quantized mean. (#4339)
add 7429997 [LICENSE] add 3rdparty
zxy844288792 opened a new pull request #4404: [AutoTVM] select model with the
most tuned schedules
URL: https://github.com/apache/incubator-tvm/pull/4404
Recently I noticed that the performance for gpu drops significantly for
conv2d with untuned workload. I did some investigation and some
u99127 commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349747601
##
File path: python/tvm/micro/base.py
##
@@ -14,129 +14,157 @@
# KIND, either express or
u99127 commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349797868
##
File path: src/runtime/micro/micro_session.h
##
@@ -174,29 +204,24 @@ class MicroSession :
u99127 commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349749186
##
File path: python/tvm/micro/device/arm/stm32f746xx.py
##
@@ -0,0 +1,123 @@
+# Licensed to
zhiics merged pull request #4339: Added tflite frontend support for quantized
mean
URL: https://github.com/apache/incubator-tvm/pull/4339
This is an automated message from the Apache Git Service.
To respond to the message,
zhiics commented on issue #4339: Added tflite frontend support for quantized
mean
URL: https://github.com/apache/incubator-tvm/pull/4339#issuecomment-557703020
Thanks @tristan-arm @anijain2305 @FrozenGene
This is an
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 00d47de [DOCS] Mention incubating in readme (#4401)
add 0f4b32f Added tflite frontend support for
niconiconi commented on issue #4403: [RFC][Cryptography] Modernize the
cryptography implementation
URL: https://github.com/apache/incubator-tvm/issues/4403#issuecomment-557700093
Some story
When I was writing Libra and it’s followup, @merrymercy come and asks “why
are you implementing
gussmith23 commented on issue #4348: [Relay] Add tests in CI which run tests
based on specific Relay feature flags
URL: https://github.com/apache/incubator-tvm/issues/4348#issuecomment-557685873
- Yeah, it seems like Steven's idea would work here. Just glob them from the
`transform`
niconiconi opened a new issue #4403: [RFC][Cryptography] Modernize the
cryptography implementation
URL: https://github.com/apache/incubator-tvm/issues/4403
Significant progress has been made during recent years due to the
development of blockchain. However, these cryptography protocols
yzhliu opened a new pull request #4402: [LICENSE] add 3rdparty licenses
URL: https://github.com/apache/incubator-tvm/pull/4402
@tqchen
This is an automated message from the Apache Git Service.
To respond to the message,
apivovarov commented on issue #4399: [Relay][Legalize] Legalize
conv2d_transpose for NHWC
URL: https://github.com/apache/incubator-tvm/pull/4399#issuecomment-557662818
@merrymercy Can you have a look as well?
All checks have passed
kevinthesun commented on issue #4399: [Relay][Legalize] Legalize
conv2d_transpose for NHWC
URL: https://github.com/apache/incubator-tvm/pull/4399#issuecomment-557649615
@anijain2305 Can you take a look?
This is an automated
tmoreau89 commented on a change in pull request #4366: [DOCS] add benchmark log
format doc
URL: https://github.com/apache/incubator-tvm/pull/4366#discussion_r349741832
##
File path: docs/dev/benchmark.rst
##
@@ -0,0 +1,116 @@
+.. Licensed to the Apache Software
tqchen commented on a change in pull request #4366: [DOCS] add benchmark log
format doc
URL: https://github.com/apache/incubator-tvm/pull/4366#discussion_r349741012
##
File path: docs/dev/benchmark.rst
##
@@ -0,0 +1,116 @@
+.. Licensed to the Apache Software Foundation
anwang2009 commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557645913
markdown has been updated to reflect removal of `runtime_config`.
`num_cpu_threads` can be optionally specified in
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 70017ef [Golang][Doc] improve the samples and doc (#4385)
add 00d47de [DOCS] Mention incubating in
tqchen merged pull request #4401: [DOCS] Mention incubating in readme
URL: https://github.com/apache/incubator-tvm/pull/4401
This is an automated message from the Apache Git Service.
To respond to the message, please log on
zhiics commented on issue #4280: [TVM][RUNTIME] A minimum example to generate
external library wrappers for DSOModule
URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-557640620
@u99127 I see, thank you. You can find the "button" like this:
tmoreau89 commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557640388
Other than that looks great
This is an automated message from
tmoreau89 commented on issue #4304: [RFC] Benchmark Performance Log Format WIP
URL: https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557639942
@anwang2009 I'd like to suggest one last modification: the removal of the
`runtime_config` since many of the fields overlap with
tmoreau89 commented on a change in pull request #4366: [DOCS] add benchmark log
format doc
URL: https://github.com/apache/incubator-tvm/pull/4366#discussion_r349731153
##
File path: docs/dev/benchmark.rst
##
@@ -0,0 +1,116 @@
+.. Licensed to the Apache Software
u99127 commented on issue #4280: [TVM][RUNTIME] A minimum example to generate
external library wrappers for DSOModule
URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-557635801
LGTM - I don't see an actual "Approve" button if clicking that's expected
from a workflow
comaniac commented on a change in pull request #4151: [AutoTVM] Added an
autotuning Config Library to store autotune results
URL: https://github.com/apache/incubator-tvm/pull/4151#discussion_r349726681
##
File path: python/tvm/autotvm/config_library.py
##
@@ -0,0 +1,279
tqchen commented on issue #4376: correct the instructions/scripts after
repository name is changed to incubator-tvm
URL: https://github.com/apache/incubator-tvm/issues/4376#issuecomment-557635144
Thanks @gittripley !
This is
tqchen commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate
URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-557634947
sounds good
This is an automated message from the Apache Git Service.
To
yzhliu commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate
URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-557630301
@tqchen RFC after tag?
This is an automated message from the Apache Git
zhiics edited a comment on issue #4280: [TVM][RUNTIME] A minimum example to
generate external library wrappers for DSOModule
URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-557628079
@u99127 Thanks. Cloud you please explicitly approve if everything looks good
to you?
zhiics commented on issue #4280: [TVM][RUNTIME] A minimum example to generate
external library wrappers for DSOModule
URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-557628079
@u99127 Thanks. Cloud you please explicitly approve if everything looks good
to you?
gittripley closed issue #4376: correct the instructions/scripts after
repository name is changed to incubator-tvm
URL: https://github.com/apache/incubator-tvm/issues/4376
This is an automated message from the Apache Git
gittripley commented on issue #4376: correct the instructions/scripts after
repository name is changed to incubator-tvm
URL: https://github.com/apache/incubator-tvm/issues/4376#issuecomment-557625990
https://github.com/apache/incubator-tvm/pull/4398 is merged.
tqchen commented on a change in pull request #4274: [µTVM] Enable AutoTVM for
ARM STM32F746XX Boards
URL: https://github.com/apache/incubator-tvm/pull/4274#discussion_r349707426
##
File path: python/tvm/contrib/binutil.py
##
@@ -45,25 +58,18 @@ def
tqchen opened a new pull request #4401: [DOCS] Mention incubating in readme
URL: https://github.com/apache/incubator-tvm/pull/4401
cc @yzhliu
This is an automated message from the Apache Git Service.
To respond to the
tqchen edited a comment on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate
URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-557614843
FYI, the common checklist used for apache incubator release
- Incubating in name
- DISCLAIMER exists
- LICENSE and
tqchen edited a comment on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate
URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-557606724
@yzhliu can we start a RFC thread before vote on dev@? just like a discuss
thread that we can get feedbacks, before we open a
tqchen commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate
URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-557614843
FYI, the common checklist used for release
- Incubating in name
- DISCLAIMER exists
- LICENSE and NOTICE are fine
- No
1 - 100 of 112 matches
Mail list logo