junrushao1994 commented on PR #71:
URL: https://github.com/apache/tvm-rfcs/pull/71#issuecomment-1133541236
@Mousius Thank you so much for your response! This makes lots of sense to
me! Also, thanks for including my personal principles in the discussion! It's
my personal principles which are
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 50997035be [ci] Restructure Jenkinsfile (#11380)
add bbc6ba362f [Meta Schedule] Add Auto-Thread Binding
huajsj opened a new pull request, #11405:
URL: https://github.com/apache/tvm/pull/11405
Currently the helper function of pipeline executor unit test like
'graph_slit' stay in the unit test file, and such function not directly related
the testing logic.
moving such helper function int
junrushao1994 commented on PR #11327:
URL: https://github.com/apache/tvm/pull/11327#issuecomment-1133523834
Is it good to merge?
--
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 the specific comme
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new d0999bbd3b [FFI] Renamed __VisitAttrs__ and __fvisit__
tqchen merged PR #11392:
URL: https://github.com/apache/tvm/pull/11392
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 50997035be [ci] Restructure Jenkinsfile (#11380)
add bbc6ba362f [Meta Schedule] Add Auto-Thread Binding Rule (#1117
junrushao1994 merged PR #11177:
URL: https://github.com/apache/tvm/pull/11177
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.ap
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 85e42b6af3 [skip ci] Fix scipy intersphinx link (#11399)
add 50997035be [ci] Restructure Jenkinsfile (#
junrushao1994 commented on PR #11404:
URL: https://github.com/apache/tvm/pull/11404#issuecomment-1133482893
CC: @zxybazh @jinhongyii
--
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 the specific
junrushao1994 opened a new pull request, #11404:
URL: https://github.com/apache/tvm/pull/11404
Previously, our auto-vectorization rule failed to vectorize some inner
loops, making our CPU performance times slower than expected. This PR fixed a
typo that causes this issue.
--
This is an a
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 4822f3e73c test Jenkins infra
new 4b568cea34 test Jenkins infra
This update added new revisio
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 5effb858b6 test Jenkins infra
new 4822f3e73c test Jenkins infra
This update added new revisio
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard db25fa70ce test Jenkins infra
new 5effb858b6 test Jenkins infra
This update added new revisio
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 888cf3918ae4d3a0ab5298e0374eccd54d5ba9d8
Author: Andrew Reusch
AuthorDate: Thu May 19 15:02:29 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 7a6b5254862425c4e8c5201fdda191b44287f701
Author: Andrew Reusch
AuthorDate: Thu May 19 15:18:02 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 8a944e166e1d457ec485591536a524152b5d3d6f
Author: Andrew Reusch
AuthorDate: Thu May 19 15:16:15 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 3d298c105bb0aef6e3c6495c7f6cb50aa2409e57
Author: Andrew Reusch
AuthorDate: Thu May 19 15:01:03 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 500a5977fd test Jenkins infra
discard b39a6285e5 Patch publish Jenkinsfiles PR.
discard 1fab2966b
driazati opened a new pull request, #11403:
URL: https://github.com/apache/tvm/pull/11403
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful information and tips. After
the pull request is submitted, please request code reviews fro
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 85e42b6af3 [skip ci] Fix scipy intersphinx link (#11399)
add 50997035be [ci] Restructure Jenkinsfile (#11380)
No new
areusch merged PR #11380:
URL: https://github.com/apache/tvm/pull/11380
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.o
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 01b472f4d0 [CI] Update CPU and GPU image (#11369)
add 72a5219aad [Schedule] Allowed typing.Tuple in
ti
mbs-octoml commented on code in PR #11382:
URL: https://github.com/apache/tvm/pull/11382#discussion_r878571872
##
python/tvm/target/target.py:
##
@@ -233,86 +233,95 @@ def canonicalize_target(target):
return Target(target)
@staticmethod
-def canonicalize_mult
mbs-octoml commented on code in PR #11382:
URL: https://github.com/apache/tvm/pull/11382#discussion_r878568482
##
tests/python/unittest/test_target_target.py:
##
@@ -353,96 +353,111 @@ def test_target_with_host():
assert tgt.host.attrs["registers_per_block"] == 32768
-d
mbs-octoml commented on code in PR #11382:
URL: https://github.com/apache/tvm/pull/11382#discussion_r878567855
##
python/tvm/target/target.py:
##
@@ -233,86 +233,95 @@ def canonicalize_target(target):
return Target(target)
@staticmethod
-def canonicalize_mult
mbs-octoml commented on PR #10963:
URL: https://github.com/apache/tvm/pull/10963#issuecomment-1133417421
Shoot, I've stepped on this in #11382, sorry about that.
In that PR I clearly distinguish the 'multi-target' APIs from the
'single-target' APIs. Everything in the tuning world need
driazati opened a new pull request, #11402:
URL: https://github.com/apache/tvm/pull/11402
- PR #11380 - [ci] Restructure Jenkinsfile
- [ci][wip] More shards
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful information an
driazati commented on code in PR #11380:
URL: https://github.com/apache/tvm/pull/11380#discussion_r878530550
##
jenkins/Jenkinsfile.j2:
##
@@ -407,503 +99,29 @@ def make(docker_type, path, make_flag) {
{% set microtvm_template_projects = ['build/microtvm_template_projects',] %}
driazati commented on code in PR #11380:
URL: https://github.com/apache/tvm/pull/11380#discussion_r878530550
##
jenkins/Jenkinsfile.j2:
##
@@ -407,503 +99,29 @@ def make(docker_type, path, make_flag) {
{% set microtvm_template_projects = ['build/microtvm_template_projects',] %}
driazati commented on code in PR #11380:
URL: https://github.com/apache/tvm/pull/11380#discussion_r878530550
##
jenkins/Jenkinsfile.j2:
##
@@ -407,503 +99,29 @@ def make(docker_type, path, make_flag) {
{% set microtvm_template_projects = ['build/microtvm_template_projects',] %}
areusch commented on code in PR #11380:
URL: https://github.com/apache/tvm/pull/11380#discussion_r878528822
##
jenkins/Jenkinsfile.j2:
##
@@ -407,503 +99,29 @@ def make(docker_type, path, make_flag) {
{% set microtvm_template_projects = ['build/microtvm_template_projects',] %}
Lunderberg commented on PR #11392:
URL: https://github.com/apache/tvm/pull/11392#issuecomment-115400
Yeah, to the best of my knowledge, it's partly historical to define allowed
outputs of name mangling, and partly to allow library implementations that
might require namespace-ignoring ma
areusch commented on code in PR #10963:
URL: https://github.com/apache/tvm/pull/10963#discussion_r878523782
##
python/tvm/autotvm/measure/measure_methods.py:
##
@@ -496,7 +497,8 @@ def set_task(self, task):
def _build_func_common(measure_input, runtime=None, check_gpu=None,
bu
areusch commented on code in PR #11304:
URL: https://github.com/apache/tvm/pull/11304#discussion_r878516958
##
tests/scripts/ci.py:
##
@@ -195,6 +195,8 @@ def docker(name: str, image: str, scripts: List[str], env:
Dict[str, str], inter
command.append("-t")
scr
areusch commented on code in PR #11362:
URL: https://github.com/apache/tvm/pull/11362#discussion_r878515012
##
apps/microtvm/zephyr/template_project/microtvm_api_server.py:
##
@@ -424,6 +423,28 @@ def _get_platform_version(self, zephyr_base: str) -> float:
return floa
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 0274d8e1f1 [TIR] Support tensorization using ldmatrix + MMA (#11355)
add 85e42b6af3 [skip ci] Fix scipy intersphinx li
masahi merged PR #11399:
URL: https://github.com/apache/tvm/pull/11399
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
masahi commented on PR #11345:
URL: https://github.com/apache/tvm/pull/11345#issuecomment-1133298471
Can you make the coding style consistent with the rest of the codebase? We
are not supposed to use `camelCase`. I can tolerate if there are only a few of
them, but I feel this change contain
cconvey commented on PR #11400:
URL: https://github.com/apache/tvm/pull/11400#issuecomment-1133289495
Here's a cleaned-up version of that output:
```
$ cat out.txt | column -s $'\t' -t -n
dtype sched_type mem_scope# 2KB vectors per tensor status
median(µsec) min(µsec)
driazati opened a new issue, #11401:
URL: https://github.com/apache/tvm/issues/11401
Failed on main for
https://github.com/apache/tvm/commit/0274d8e1f124cecc159abf3234251bf010784581
https://github.com/apache/tvm/runs/6529970442?check_suite_focus=true
```
No numpy version specifi
junrushao1994 commented on PR #11392:
URL: https://github.com/apache/tvm/pull/11392#issuecomment-1133284873
TIL didn't know that before!
CC: @tqchen
--
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
junrushao1994 commented on PR #11384:
URL: https://github.com/apache/tvm/pull/11384#issuecomment-1133280849
Thanks @manupa-arm for the context! It makes sense to me now :-) Yeah I
agree with you that it would be better to keep `tvm_ssize_t` instead.
--
This is an automated message from th
masahi commented on code in PR #11389:
URL: https://github.com/apache/tvm/pull/11389#discussion_r878504009
##
python/tvm/topi/cuda/batch_matmul.py:
##
@@ -367,7 +367,7 @@ def _schedule_batch_matmul_int8(cfg, s, output):
# dp4a tensorize
target = tvm.target.Target.cur
cconvey commented on PR #11400:
URL: https://github.com/apache/tvm/pull/11400#issuecomment-1133278194
Output is basically unchanged from the previous table implementation:
```
dtype sched_type mem_scope # 2KB vectors per tensor
status median(µsec)min(µsec)
cconvey commented on PR #11400:
URL: https://github.com/apache/tvm/pull/11400#issuecomment-1133276623
CC: @Lunderberg
--
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 the specific comment.
To un
Lunderberg commented on PR #11269:
URL: https://github.com/apache/tvm/pull/11269#issuecomment-1133276452
Current CI failures due to Scipy URL change, should restart CI after #11399
lands.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on
cconvey opened a new pull request, #11400:
URL: https://github.com/apache/tvm/pull/11400
Generalize the benchmark-table code to support arbitrary
indendent values. This supports future changes to the benchmark
code.
--
This is an automated message from the Apache Git Service.
To resp
Lunderberg opened a new pull request, #11399:
URL: https://github.com/apache/tvm/pull/11399
Follow-up from https://github.com/apache/tvm/pull/10181, as the URL has
changed again in https://github.com/scipy/scipy/pull/16221. From [this
comment](https://github.com/scipy/scipy/issues/14267#is
areusch commented on code in PR #11393:
URL: https://github.com/apache/tvm/pull/11393#discussion_r878491391
##
tests/python/unittest/test_tvmscript_syntax_sugar.py:
##
@@ -347,4 +347,6 @@ def mma_sync_m16n16k16_desc_manual(a: T.handle, b:
T.handle, c: T.handle) -> Non
if _
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 710f07e61d test Jenkins infra
discard 03e1f202bf Patch publish Jenkinsfiles PR.
discard 1e2f28eb0
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 5cd2a0d14acfe7bac0204e1f25386e8033404c79
Author: Andrew Reusch
AuthorDate: Thu May 19 15:01:03 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 1fab2966ba579839d57c057ec443818d352fc205
Author: Andrew Reusch
AuthorDate: Thu May 19 15:18:02 2022 -
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 07d91fa041 Fix function number datatype from char to uint16_t (#11365)
add c8d2283705 Fix array pointer
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 1e2f28eb06878cc08ae6b7aa297bce7fdfe1e532
Author: Andrew Reusch
AuthorDate: Thu May 19 15:18:02 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 03e1f202bf061b4191b9d3c17e9deb53d5d10074
Author: Andrew Reusch
AuthorDate: Thu May 19 15:26:47 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 4cbde7399bedc47d0b3bd3e75b6f1a3f676b269f
Author: Andrew Reusch
AuthorDate: Thu May 19 15:01:03 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit b39a6285e5ac74bd03319a4b9726c8147702bbe0
Author: Andrew Reusch
AuthorDate: Thu May 19 15:26:47 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 8155300f8f fix freeze-deps computation of docker image name
discard b7770381e0 try to fix image ma
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit b60fa1c386759e662e1d90873c6a45232ba89e6e
Author: Andrew Reusch
AuthorDate: Thu May 19 15:16:15 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 9088cff9d90bbfc3827a39a6ab3bb0cc753f0d20
Author: Andrew Reusch
AuthorDate: Thu May 19 15:16:15 2022 -
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 399b7a7cc82520884f99be0233dae94fbd7e292e
Author: Andrew Reusch
AuthorDate: Thu May 19 15:02:29 2022 -
argrento commented on code in PR #11241:
URL: https://github.com/apache/tvm/pull/11241#discussion_r878432610
##
.github/workflows/main.yml:
##
@@ -38,59 +38,124 @@ jobs:
MacOS:
runs-on: macOS-latest
steps:
-- uses: actions/checkout@v2
- with:
-submo
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 0274d8e1f1 [TIR] Support tensorization using ldmatrix +
vinx13 merged PR #11355:
URL: https://github.com/apache/tvm/pull/11355
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch areusch/freeze-dependencies
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 5f47ca5590993a6f4a68c9e43f529befcbc3bf67
Author: Andrew Reusch
AuthorDate: Thu May 19 15:02:29 2022 -
areusch merged PR #11045:
URL: https://github.com/apache/tvm/pull/11045
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.o
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 72a5219aad [Schedule] Allowed typing.Tuple in
tir.schedule._type_checker (#11289)
add febae407ed [docs] Add lightwei
rkimball opened a new pull request, #11398:
URL: https://github.com/apache/tvm/pull/11398
This case was removed to support dimensions > 2 but is needed for dimensions
== 2
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub a
vinx13 commented on PR #70:
URL: https://github.com/apache/tvm-rfcs/pull/70#issuecomment-1133153361
@wrongtest I've thought about the option A3 vs A4. From the parsing /
translation from TVM script to TIR, it is acceptable to have `T.allocate`
translated to `Allocate + DeclBuffer` two nodes
Lunderberg commented on code in PR #11269:
URL: https://github.com/apache/tvm/pull/11269#discussion_r878384725
##
python/tvm/tir/schedule/schedule.py:
##
@@ -2114,25 +2114,111 @@ def after_unannotate(a: T.handle, b: T.handle) -> None:
## Schedule: Layout transform
vinx13 commented on code in PR #70:
URL: https://github.com/apache/tvm-rfcs/pull/70#discussion_r878382048
##
rfcs/0070-introducing-decl-buffer.md:
##
@@ -0,0 +1,210 @@
+- Feature Name: introducing-decl-buffer
+- Author: Wuwei Lin (@vinx13), Eric Lunderberg (@Lunderberg)
+- Start
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 01b472f4d0 [CI] Update CPU and GPU image (#11369)
add 72a5219aad [Schedule] Allowed typing.Tuple in
tir.schedule._type
vinx13 merged PR #11289:
URL: https://github.com/apache/tvm/pull/11289
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
vinx13 commented on code in PR #11269:
URL: https://github.com/apache/tvm/pull/11269#discussion_r878367921
##
python/tvm/tir/schedule/schedule.py:
##
@@ -2114,25 +2114,111 @@ def after_unannotate(a: T.handle, b: T.handle) -> None:
## Schedule: Layout transformatio
mbs-octoml commented on PR #60:
URL: https://github.com/apache/tvm-rfcs/pull/60#issuecomment-1133139602
One more collage/uma overlap aspect: Collage distinguishes 'registered'
backends (ie just TargetKinds) from 'activated' backends (ie Target objects in
the provided build targets). I think
areusch commented on PR #11386:
URL: https://github.com/apache/tvm/pull/11386#issuecomment-1133121410
@mbs-octoml @altanh can you take a look?
--
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 the
mehrdadh commented on code in PR #11395:
URL: https://github.com/apache/tvm/pull/11395#discussion_r878340561
##
tests/python/contrib/test_hexagon/test_autotvm.py:
##
@@ -0,0 +1,148 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license ag
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 01b472f4d0 [CI] Update CPU and GPU image (#11369)
01b4
areusch merged PR #11369:
URL: https://github.com/apache/tvm/pull/11369
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.o
lhutton1 opened a new pull request, #11397:
URL: https://github.com/apache/tvm/pull/11397
All codegen tests have been running with a representative dataset between
0,1 which masked an output mismatch in Leaky ReLU when compared to TFLite
kernels. This issue can be replicated by replacing th
csullivan opened a new issue, #11396:
URL: https://github.com/apache/tvm/issues/11396
### Expected behavior
Each built runtime module should be sent via the HexagonSession from host ->
android -> hexagon for performance trials.
### Actual behavior
There are errors in th
csullivan commented on PR #11395:
URL: https://github.com/apache/tvm/pull/11395#issuecomment-1133069953
cc @farshidsp @mehrdadh
--
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 the specific comme
csullivan opened a new pull request, #11395:
URL: https://github.com/apache/tvm/pull/11395
Test is currently disabled. See issue:
--
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 the specific com
grant-arm commented on issue #11394:
URL: https://github.com/apache/tvm/issues/11394#issuecomment-1133054411
Thanks for raising this @SebastianBoblestETAS. We will take a look at it.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to Gi
SebastianBoblestETAS opened a new issue, #11394:
URL: https://github.com/apache/tvm/issues/11394
I already reported this issue here:
https://discuss.tvm.apache.org/t/problem-with-allocateconstnodes-in-cmsis-nn-code/12806
It seems that AllocateConstNodes can be overwritten in models
gigiblender opened a new pull request, #11393:
URL: https://github.com/apache/tvm/pull/11393
This PR replaces the test call to `pytest.main`
```
sys.exit(pytest.main([test_file] + sys.argv[1:]))
```
with a call to a [utility
function:](https://github.com/gigiblender/tvm/blob/056
Lunderberg opened a new pull request, #11392:
URL: https://github.com/apache/tvm/pull/11392
All names beginning with two underscores are reserved for the compiler and
standard library, even if they occur inside a class or namespace ([relevant
stackoverflow](https://stackoverflow.com/questio
tqchen commented on PR #71:
URL: https://github.com/apache/tvm-rfcs/pull/71#issuecomment-1133026002
Thanks folks for discussions. I think they summarizes to the following points
- Q0: Subfield grouping (e.g. features) or simply leave as top-level attrs
- Q1: Folder structure: `targe
tqchen commented on PR #71:
URL: https://github.com/apache/tvm-rfcs/pull/71#issuecomment-1133013784
Thanks folks for discussions. I think they summarizes to the following points
- Q0: Subfield grouping (e.g. features) or simply leave as top-level attrs
- Q1: Folder structure: `targe
lhutton1 commented on code in PR #11208:
URL: https://github.com/apache/tvm/pull/11208#discussion_r878091500
##
src/relay/backend/aot/annotate_used_memory.cc:
##
@@ -0,0 +1,156 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license
KJlaccHoeUM9l commented on code in PR #11241:
URL: https://github.com/apache/tvm/pull/11241#discussion_r878211269
##
.github/workflows/main.yml:
##
@@ -38,59 +38,124 @@ jobs:
MacOS:
runs-on: macOS-latest
steps:
-- uses: actions/checkout@v2
- with:
-
KJlaccHoeUM9l opened a new pull request, #11391:
URL: https://github.com/apache/tvm/pull/11391
[PR](https://github.com/apache/tvm/pull/11003) has added the ability to skip
copying data when creating input `NDArray` tensors if the source input is in
`DLTensor` format.
However, when ad
petuca commented on issue #10614:
URL: https://github.com/apache/tvm/issues/10614#issuecomment-1132921211
Same story here. I can't reproduce the issue on my latest commit. I got the
same shapes and results for predictions and output. Is this issue solved?
@leeexyz @JoeyTPChou @masahi
Mousius commented on PR #71:
URL: https://github.com/apache/tvm-rfcs/pull/71#issuecomment-1132872196
Hi @junrushao1994, thanks for the elaborate reply 😸 I don't want to debate
our personal principles but I appreciate you sharing them and will reference
them where I can.
> **Current
lhutton1 commented on code in PR #11208:
URL: https://github.com/apache/tvm/pull/11208#discussion_r878085445
##
src/relay/backend/aot/annotate_used_memory.cc:
##
@@ -0,0 +1,156 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license
lhutton1 commented on code in PR #11208:
URL: https://github.com/apache/tvm/pull/11208#discussion_r878083413
##
src/relay/backend/aot/annotate_used_memory.cc:
##
@@ -0,0 +1,156 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 3248793dd8 Add Conv3D bindings (#11381)
add 07d91fa041 Fix function number datatype from char to uint16
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 909851c2f5 [ci][easy] Fix parameters for macros (#11377)
add 3248793dd8 Add Conv3D bindings (#11381)
N
PTTQ opened a new pull request, #11390:
URL: https://github.com/apache/tvm/pull/11390
Even if the `vta_config.json` on the host side and the hardware side are the
same, it will be judged as a different configuration, and the libvta.so file
will be rebuilt.
I found that the reason is that
1 - 100 of 129 matches
Mail list logo
