Beya2019 commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486813081
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, layou
Beya2019 commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486813081
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, layou
junrushao1994 commented on a change in pull request #6450:
URL: https://github.com/apache/incubator-tvm/pull/6450#discussion_r486809195
##
File path: CMakeLists.txt
##
@@ -109,6 +109,22 @@ if(MSVC)
endif(${flag_var} MATCHES "/MD")
endforeach(flag_var)
endif()
+
junrushao1994 commented on pull request #6450:
URL: https://github.com/apache/incubator-tvm/pull/6450#issuecomment-690909842
It looks very clean now!
I actually found the unicode in data_layout.h: they are in line 317 and 318,
which is "…"
--
lsy643 edited a comment on pull request #6108:
URL: https://github.com/apache/incubator-tvm/pull/6108#issuecomment-690903238
@yongwww
I have added a test case for nms cuda version in `test_op_level5.p` with
test data assumed getting from a `get_valid_count`.
Since there is no `re
kevinthesun commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486803979
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, la
kevinthesun commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486803979
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, la
kevinthesun commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486803979
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, la
lsy643 commented on pull request #6108:
URL: https://github.com/apache/incubator-tvm/pull/6108#issuecomment-690903238
@yongwww
I have added a test case for nms cuda version in `test_op_level5.p` with
test data assumed getting from a `get_valid_count`.
Since there is no `rearrange
kevinthesun commented on pull request #6449:
URL: https://github.com/apache/incubator-tvm/pull/6449#issuecomment-690898948
@masahi These changes are mainly for torch vision rcnn models which enhances
current features. There is another PR adding some backend stuffs. After that I
can add e2e
masahi commented on pull request #6447:
URL: https://github.com/apache/incubator-tvm/pull/6447#issuecomment-690898056
Thanks @t-vi @junrushao1994 @tqchen
This is an automated message from the Apache Git Service.
To respond t
masahi merged pull request #6447:
URL: https://github.com/apache/incubator-tvm/pull/6447
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.
masahi 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 01460e0 ROCm: use GcnArch for mcpu and A
kevinthesun commented on pull request #6388:
URL: https://github.com/apache/incubator-tvm/pull/6388#issuecomment-690897350
Thanks @zhiics @mbrookhart @yongwww @masahi
This is an automated message from the Apache Git Service.
This is an automated email from the ASF dual-hosted git repository.
kevinthesun 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 1228111 [Relay][Topi][Op]Advanced i
kevinthesun merged pull request #6388:
URL: https://github.com/apache/incubator-tvm/pull/6388
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 edited a comment on pull request #6450:
URL: https://github.com/apache/incubator-tvm/pull/6450#issuecomment-690861794
cc @tmoreau89 @rkimball @jroesch
This is an automated message from the Apache Git Service.
To respo
tqchen opened a new pull request #6450:
URL: https://github.com/apache/incubator-tvm/pull/6450
This PR fixes various warnings bought by MSVC.
TODO: deprecate `__tvm_main__` symbol and update
testcase so windows works as normal.
tqchen commented on pull request #6450:
URL: https://github.com/apache/incubator-tvm/pull/6450#issuecomment-690861794
cc @tmoreau89 @rkimball
This is an automated message from the Apache Git Service.
To respond to the messag
masahi edited a comment on pull request #6449:
URL: https://github.com/apache/incubator-tvm/pull/6449#issuecomment-690855865
@kevinthesun Thanks for working on this. Can you split this into multiple
PRs? In particular, besides the new op conversion, you made many non trivial
changes to exi
masahi commented on pull request #6449:
URL: https://github.com/apache/incubator-tvm/pull/6449#issuecomment-690855865
@kevinthesun Thanks for working on this. Can you split this into multiple
PRs? In particular, besides the new op conversion, you made many non trivial
changes to existng op
areusch commented on pull request #6334:
URL: https://github.com/apache/incubator-tvm/pull/6334#issuecomment-690854878
@tqchen @liangfu please take another look when you have a minute
This is an automated message from the Apa
masahi commented on pull request #6449:
URL: https://github.com/apache/incubator-tvm/pull/6449#issuecomment-690846159
cc @siju-samuel @t-vi
This is an automated message from the Apache Git Service.
To respond to the message,
masahi commented on a change in pull request #6446:
URL: https://github.com/apache/incubator-tvm/pull/6446#discussion_r486745778
##
File path: tests/python/frontend/onnx/test_forward.py
##
@@ -425,6 +425,45 @@ def test_gather():
verify_gather((4, 3, 5, 6), [[2, 1, 0, 0]],
siju-samuel commented on a change in pull request #6446:
URL: https://github.com/apache/incubator-tvm/pull/6446#discussion_r486744994
##
File path: tests/python/frontend/onnx/test_forward.py
##
@@ -425,6 +425,45 @@ def test_gather():
verify_gather((4, 3, 5, 6), [[2, 1, 0,
Beya2019 commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486742150
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, layou
Beya2019 commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486734730
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, layou
kevinthesun opened a new pull request #6449:
URL: https://github.com/apache/incubator-tvm/pull/6449
Some necessary improvements for pytorch od models.
@zhiics @yongwww @masahi
This is an automated message from the
jroesch opened a new pull request #6448:
URL: https://github.com/apache/incubator-tvm/pull/6448
cc @tqchen this one applies formatting without CI machinery.
This is an automated message from the Apache Git Service.
To respon
jroesch commented on pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#issuecomment-690821576
@tqchen recommended that we first format the entire code base using these
settings then try to land the CI parts, going to open a second PR with the
fully formatted repo.
tqchen merged pull request #6444:
URL: https://github.com/apache/incubator-tvm/pull/6444
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 ecba2f3 [Relay][Op] Fix Reshape Compute (#6396)
add 355720e CUDA: broaden path detection (#6444)
No ne
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 aeef16d [QNN][Relay] Fixed bug in quantized conv2d. (#6420)
add ecba2f3 [Relay][Op] Fix Reshape Co
kevinthesun merged pull request #6396:
URL: https://github.com/apache/incubator-tvm/pull/6396
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
kevinthesun commented on pull request #6396:
URL: https://github.com/apache/incubator-tvm/pull/6396#issuecomment-690805570
Thanks @mbrookhart @zhiics @tqchen @electriclilies
This is an automated message from the Apache Git S
kevinthesun commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486679507
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, la
kevinthesun commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486679507
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, la
kevinthesun commented on a change in pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#discussion_r486679507
##
File path: python/tvm/relay/op/vision/rcnn.py
##
@@ -24,7 +24,7 @@ def roi_align(data, rois, pooled_size, spatial_scale,
sample_ratio=-1, la
kevinthesun commented on pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#issuecomment-690774753
Yeah. As @anijain2305 mentioned, we only have ```roi_align_nchw``` in topi.
This is an automated messa
t-vi commented on pull request #6447:
URL: https://github.com/apache/incubator-tvm/pull/6447#issuecomment-690731565
@junrushao1994 Yeah, and I'll admit that I wouldn't have spotted it without
trying to run it on the hardware that is particular about it...
I actually hope that we might be
comaniac commented on a change in pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#discussion_r486620292
##
File path: tests/lint/git-black.sh
##
@@ -0,0 +1,72 @@
+#!/bin/bash
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more con
junrushao1994 edited a comment on pull request #6447:
URL: https://github.com/apache/incubator-tvm/pull/6447#issuecomment-690711679
I see. So there are actually two version, one is ApiVersion, which is used
to decide whether to add "-code-object-v3" into mattr; Another is GcnArch,
which is
junrushao1994 commented on pull request #6447:
URL: https://github.com/apache/incubator-tvm/pull/6447#issuecomment-690711679
I see. So there are actually two version, one ApiVersion, which is used to
decide whether to add "-code-object-v3" into mattr; Another is GcnArch, which
is used to d
t-vi opened a new pull request #6447:
URL: https://github.com/apache/incubator-tvm/pull/6447
This is a ROCm followup for #6347 bringing the code that was moved from
src/target/llvm/codegen_amdgpu.cc to src/target/target_kind.cc closer to the
old mechanism for compute arch autodetection.
masahi opened a new pull request #6446:
URL: https://github.com/apache/incubator-tvm/pull/6446
https://github.com/onnx/onnx/blob/master/docs/Operators.md#GatherElements
This is required to convert decision trees from hummingbird to Relay.
please review @siju-samuel @jwfromm @mb
t-vi commented on pull request #6347:
URL: https://github.com/apache/incubator-tvm/pull/6347#issuecomment-690705823
I'll just send a PR in a minute or so.
This is an automated message from the Apache Git Service.
To respond t
junrushao1994 commented on pull request #6347:
URL: https://github.com/apache/incubator-tvm/pull/6347#issuecomment-690703438
@t-vi I see. We should change this line:
https://github.com/apache/incubator-tvm/blob/master/src/target/target_kind.cc#L176,
from `runtime::kApiVersion` to `runtime:
junrushao1994 edited a comment on pull request #6347:
URL: https://github.com/apache/incubator-tvm/pull/6347#issuecomment-690703438
@t-vi I see. We should change this line:
https://github.com/apache/incubator-tvm/blob/master/src/target/target_kind.cc#L176,
from `runtime::kApiVersion` to `r
junrushao1994 commented on pull request #6347:
URL: https://github.com/apache/incubator-tvm/pull/6347#issuecomment-690699114
@t-vi Yes, the detection logic used previously in amdgpu codegen is here:
https://github.com/apache/incubator-tvm/blob/e5b793f39fd5b4f84b0aedf06aa376ebe45cf2bc/src/ta
t-vi commented on pull request #6347:
URL: https://github.com/apache/incubator-tvm/pull/6347#issuecomment-690694805
The ROCm default detection seems to have been mangled to confuse ROCm
version (software) with compute arch (hardware, e.g. gfx). I'll try to fix it.
jroesch commented on pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#issuecomment-690676307
@junrushao1994 @comaniac @areusch I just added the scripts and cleaned some
things up, take another pass if you can
-
anijain2305 commented on pull request #6430:
URL: https://github.com/apache/incubator-tvm/pull/6430#issuecomment-690618685
@tqchen Do you have any suggestions here?
This is an automated message from the Apache Git Service.
To
lhutton1 commented on pull request #6430:
URL: https://github.com/apache/incubator-tvm/pull/6430#issuecomment-690617359
Yep that's correct. I think the current PR has one advantage being that a
"custom" layout is explicitly defined and passed to convert layout as opposed
to overriding a fu
jroesch commented on a change in pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#discussion_r486554772
##
File path: pyproject.toml
##
@@ -0,0 +1,29 @@
+[tool.black]
+line-length = 88
Review comment:
@tqchen confirmed this should be 100.
anijain2305 commented on pull request #6430:
URL: https://github.com/apache/incubator-tvm/pull/6430#issuecomment-690600943
Yes, that makes sense. Thanks for explaining!
Yes, if we want to go through something like `TempOpAttr`, we need that
functionality in C++.
Is your curren
jroesch commented on a change in pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#discussion_r486547524
##
File path: tests/lint/git-black.sh
##
@@ -0,0 +1,76 @@
+#!/bin/bash
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more cont
jroesch commented on pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#issuecomment-690594159
@areusch @tqchen @comaniac I can rollback the formatting, the first 3 or 4
commits were focused on formatting then I went through the process to see if it
would actually w
comaniac commented on pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#issuecomment-690587908
cc @masahi @junrushao1994 @tqchen for a final review.
This is an automated message from the Apache Git Se
comaniac commented on a change in pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r486517802
##
File path: python/tvm/driver/tvmc/compiler.py
##
@@ -0,0 +1,280 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more cont
lhutton1 commented on pull request #6430:
URL: https://github.com/apache/incubator-tvm/pull/6430#issuecomment-690584984
So since convert layout is part of preprocessing the module in the optimize
step before codegen
(https://github.com/apache/incubator-tvm/blob/master/src/relay/backend/con
areusch commented on a change in pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#discussion_r486529234
##
File path: tests/lint/git-black.sh
##
@@ -0,0 +1,76 @@
+#!/bin/bash
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more cont
anijain2305 merged pull request #6420:
URL: https://github.com/apache/incubator-tvm/pull/6420
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.
anijain2305 pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from b81bdee [Relay] Add Defunctionalization Pass (#6400)
add aeef16d [QNN][Relay] Fixed bug in quanti
anijain2305 commented on pull request #6420:
URL: https://github.com/apache/incubator-tvm/pull/6420#issuecomment-690543418
Thanks @jainris This is merged!
This is an automated message from the Apache Git Service.
To respond t
comaniac commented on a change in pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#discussion_r486506436
##
File path: tests/lint/git-black.sh
##
@@ -0,0 +1,76 @@
+#!/bin/bash
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more con
t-vi closed pull request #6440:
URL: https://github.com/apache/incubator-tvm/pull/6440
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
t-vi commented on pull request #6440:
URL: https://github.com/apache/incubator-tvm/pull/6440#issuecomment-690536150
@junrushao1994 Right, thank you! @masahi @tqchen sorry for the noise. I had
searched for rocm/mcpu patches but missed the more general one.
-
anijain2305 commented on pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443#issuecomment-690523605
Is there a `NHWC` topi implementation for `roi_align`? If not, this will
cause compilation failure for traditional TVM targets.
--
This is an automated email from the ASF dual-hosted git repository.
marisa pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from e6374dc Fix broadcast shape (#6422)
add b81bdee [Relay] Add Defunctionalization Pass (#6400)
No new r
junrushao1994 commented on pull request #6437:
URL: https://github.com/apache/incubator-tvm/pull/6437#issuecomment-690520497
It is a bit hard to review 1000 files...maybe just take a look at the
pyproject.toml file and assume other parts are correct?
--
MarisaKirisame merged pull request #6400:
URL: https://github.com/apache/incubator-tvm/pull/6400
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL ab
MarisaKirisame commented on pull request #6400:
URL: https://github.com/apache/incubator-tvm/pull/6400#issuecomment-690407237
Thx @hypercubestart @yzhliu .
This is an automated message from the Apache Git Service.
To respond
giuseros opened a new pull request #6445:
URL: https://github.com/apache/incubator-tvm/pull/6445
### High level description of the submission
We added two new intrinsics in: `topi/arm_cpu/tensor_intrin.py`, namely
- `mmla4x4`: compute a matrix multiplication between tile `A(4,4)` and t
anijain2305 edited a comment on pull request #6430:
URL: https://github.com/apache/incubator-tvm/pull/6430#issuecomment-690504454
I think calling ConvertLayout in C++ should be ok. The thing that I don't
fully understand is why do we need to set the `FTVMConvertOpLayout` in C++? Is
there a
anijain2305 commented on pull request #6430:
URL: https://github.com/apache/incubator-tvm/pull/6430#issuecomment-690504454
I think calling ConvertLayout in C++ should be ok. The thing that I don't
fully understand is why do we need to set the `FTVMConvertOpLayout` in C++? Is
there a way to
lhutton1 commented on pull request #6430:
URL: https://github.com/apache/incubator-tvm/pull/6430#issuecomment-690476905
Thanks for the pointer @anijain2305. I do agree this is a better approach. I
have an example working on my end for my use-case, although it seems quite
messy. Setting tem
junrushao1994 commented on pull request #6440:
URL: https://github.com/apache/incubator-tvm/pull/6440#issuecomment-690464393
Hmmm I think the issue has been fixed by #6369
This is an automated message from the Apache Git Serv
tqchen commented on pull request #6440:
URL: https://github.com/apache/incubator-tvm/pull/6440#issuecomment-690456262
@t-vi please rebase against the master to resolve conflicts
This is an automated message from the Apache Gi
tqchen commented on pull request #6396:
URL: https://github.com/apache/incubator-tvm/pull/6396#issuecomment-690413648
@kevinthesun please rebase against the master
This is an automated message from the Apache Git Service.
To
zhiics merged pull request #6422:
URL: https://github.com/apache/incubator-tvm/pull/6422
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
zhiics commented on pull request #6422:
URL: https://github.com/apache/incubator-tvm/pull/6422#issuecomment-690386154
Thanks @kevinthesun @jroesch @mbrookhart @electriclilies @icemelon9
This is an automated message from the
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 6b6661e [Target] Tags, Composite Target, Unified Interface (#6369)
add e6374dc Fix broadcast shape (#6422
leandron edited a comment on pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#issuecomment-690379907
There was an issue we discovered with `ConvertLayout` when running the new
tests introduced here, once #6442 is merged, all the tests should pass.
@comaniac
leandron commented on pull request #6302:
URL: https://github.com/apache/incubator-tvm/pull/6302#issuecomment-690379907
There was an issue we discovered with ConvertLayout when running the new
tests introduced here, once #6442 is merged, all the tests should pass.
@comaniac would you
tqchen commented on pull request #6369:
URL: https://github.com/apache/incubator-tvm/pull/6369#issuecomment-690375070
Thanks @junrushao1994 @comaniac
This is an automated message from the Apache Git Service.
To respond to th
tqchen merged pull request #6369:
URL: https://github.com/apache/incubator-tvm/pull/6369
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 b05aa96 [Rust] Improve the error reporting in build.rs files by using
anyhow. (#6401)
add 6b6661e [Tar
junrushao1994 commented on pull request #6369:
URL: https://github.com/apache/incubator-tvm/pull/6369#issuecomment-690365841
@tqchen CI is green. Would you like to take another look? Thanks!
This is an automated message from
tqchen commented on pull request #6401:
URL: https://github.com/apache/incubator-tvm/pull/6401#issuecomment-690364824
Thanks @imalsogreg @adelbertc @jroesch !
This is an automated message from the Apache Git Service.
To respo
tqchen merged pull request #6401:
URL: https://github.com/apache/incubator-tvm/pull/6401
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 3a4e61a [METAL] set MTLBuffer purgeable state (#6376) (#6438)
add b05aa96 [Rust] Improve the error repo
tqchen commented on issue #6441:
URL: https://github.com/apache/incubator-tvm/issues/6441#issuecomment-690360234
cc @jwfromm @masahi
This is an automated message from the Apache Git Service.
To respond to the message, please
tqchen commented on issue #6376:
URL: https://github.com/apache/incubator-tvm/issues/6376#issuecomment-690358667
Thanks @jacobpostman @vathysjacob it would also be nice if you can
experiment further about what happens to the rest of the memory
-
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 8705cea [Relay, Torch] Fix stack op axis check, support torch::stack
conversion for a static list (#6433)
tqchen merged pull request #6438:
URL: https://github.com/apache/incubator-tvm/pull/6438
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
t-vi commented on pull request #6444:
URL: https://github.com/apache/incubator-tvm/pull/6444#issuecomment-690298687
@tqchen @junrushao1994 @vinx13 I think the last PRs on this file were
reviewed by you.
This is an autom
t-vi commented on pull request #6444:
URL: https://github.com/apache/incubator-tvm/pull/6444#issuecomment-690255750
At some point we might ask which supported cuda versions are in the else
case (looks like this is only CUDA < 9 to me).
-
t-vi opened a new pull request #6444:
URL: https://github.com/apache/incubator-tvm/pull/6444
Debian/Ubuntu repackaged CUDA has slightly different paths
Also, add CUDA versions 10.1, 10.2.
This is an automated message f
Beya2019 opened a new pull request #6443:
URL: https://github.com/apache/incubator-tvm/pull/6443
RFC: #4335
https://discuss.tvm.ai/t/layout-conversion-pass/4009
add aoi_align operator(in maskrcnn) convert_op_layout and related test case
in test_pass_convert_op_layout.py .
W
Beya2019 closed pull request #6439:
URL: https://github.com/apache/incubator-tvm/pull/6439
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
1 - 100 of 121 matches
Mail list logo