mehrdadh commented on pull request #10841:
URL: https://github.com/apache/tvm/pull/10841#issuecomment-1084167046
cc @supersat
--
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
mehrdadh commented on pull request #10841:
URL: https://github.com/apache/tvm/pull/10841#issuecomment-1084165784
cc @areusch @driazati @kparzysz-quic @cconvey
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL a
mehrdadh opened a new pull request #10841:
URL: https://github.com/apache/tvm/pull/10841
This PR makes required adjustments to update Hexagon CI image to ubuntu
20.04. The base image is built by Ubuntu 20.04
--
This is an automated message from the Apache Git Service.
To respond to t
This is an automated email from the ASF dual-hosted git repository.
comaniac pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 5cacecc [CUBLAS] Add support for nn.dense and nn.batch_matmul (#10826)
add 5814fdd prune dnnl subgraph, and add r
comaniac commented on pull request #10835:
URL: https://github.com/apache/tvm/pull/10835#issuecomment-1084158288
Thanks @crazydemo
--
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 c
comaniac merged pull request #10835:
URL: https://github.com/apache/tvm/pull/10835
--
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-unsubsc
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 45dea9197b69a508e15794ac357c0175ec7265f9
Author: Masahiro Masuda
AuthorDate: Thu Mar 31 15:32:33 2022 +0900
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git.
discard 25dea1a validating the new cpu image
add b5e0479 [Pass][Bugfix] StorageFlatten, buffer var definitions
SebastianBoblestETAS commented on pull request #9950:
URL: https://github.com/apache/tvm/pull/9950#issuecomment-1084089033
Hi,
I would postpone resolving this PR until we have finished our work the TIR
export: https://discuss.tvm.apache.org/t/export-tir-to-json/12329/6 if this is
ok.
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 42985c3 [Hexagon] Handle v69 in RPC launcher on simulator (#10829)
add 5cacecc [CUBLAS] Add support for nn.dense an
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 6af3f36 [Hexagon] Pass extra parameters to link_params via Map
(#10830)
add 42985c3 [Hexagon] Handle v69 in RPC la
masahi merged pull request #10826:
URL: https://github.com/apache/tvm/pull/10826
--
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.
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 72c761c [MetaSchedule] Fine-Grained Rewrite Unbound Block (#10823)
add 6af3f36 [Hexagon] Pass extra parameters to l
masahi merged pull request #10829:
URL: https://github.com/apache/tvm/pull/10829
--
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.
masahi merged pull request #10830:
URL: https://github.com/apache/tvm/pull/10830
--
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.
masahi commented on pull request #10783:
URL: https://github.com/apache/tvm/pull/10783#issuecomment-1084069179
I assume this PR is no longer necessary, since we merged your another PR
https://github.com/apache/tvm/pull/10797
--
This is an automated message from the Apache Git Service.
To
masahi closed pull request #10783:
URL: https://github.com/apache/tvm/pull/10783
--
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.
masahi commented on a change in pull request #10839:
URL: https://github.com/apache/tvm/pull/10839#discussion_r839161718
##
File path: python/tvm/topi/arm_cpu/tensor_intrin.py
##
@@ -614,21 +614,22 @@ def _instr(index):
ib.emit(outs[0].vstore(0, tvm.tir.const(0
masahi commented on a change in pull request #10839:
URL: https://github.com/apache/tvm/pull/10839#discussion_r839161718
##
File path: python/tvm/topi/arm_cpu/tensor_intrin.py
##
@@ -614,21 +614,22 @@ def _instr(index):
ib.emit(outs[0].vstore(0, tvm.tir.const(0
masahi commented on a change in pull request #10839:
URL: https://github.com/apache/tvm/pull/10839#discussion_r839160185
##
File path: tests/python/topi/python/test_topi_conv2d_int8.py
##
@@ -364,7 +365,7 @@ def get_ref_data():
# ),
]
-# TODO(tvm-team): Prop
MargaretQian commented on a change in pull request #10722:
URL: https://github.com/apache/tvm/pull/10722#discussion_r839156904
##
File path: tests/python/driver/tvmc/test_runner.py
##
@@ -79,11 +79,47 @@ def test_run_tflite_module__with_profile__valid_input(
pytest.importo
masahi commented on issue #10673:
URL: https://github.com/apache/tvm/issues/10673#issuecomment-1084051576
[test_topi_conv2d_int8.py::verify_conv2d_NCHWc_int8](https://github.com/apache/tvm/blob/b01e3fc4d21bba898a5ea17d526013c52ea720eb/tests/python/topi/python/test_topi_conv2d_int8.py#L383-L
jinfagang opened a new issue #10840:
URL: https://github.com/apache/tvm/issues/10840
Normally, from docs it says, the static lib can be get function out using
this:
```
tvm::runtime::Module mod_tvmlib =
(*tvm::runtime::Registry::Get("runtime.SystemLib"))();
```
masahi opened a new pull request #10839:
URL: https://github.com/apache/tvm/pull/10839
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 from
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 10f037f [ci][docker] Remove nvidia ml repository before updating
(#10828)
add 72c761c [MetaSchedule
areusch commented on a change in pull request #10785:
URL: https://github.com/apache/tvm/pull/10785#discussion_r839122408
##
File path: include/tvm/tir/usmp/utils.h
##
@@ -41,10 +41,16 @@ constexpr const char* kUSMPEnableOption = "tir.usmp.enable";
* \brief PassContext option
crazydemo opened a new pull request #10838:
URL: https://github.com/apache/tvm/pull/10838
This PR would like to change the default weight layout for
`conv3d_transpose` from `OIDHW` to `IODHW`.
I find that, for conv3d_transpose the weight shape is in order of `(I, O, D,
H, W)`, which
crazydemo opened a new pull request #10837:
URL: https://github.com/apache/tvm/pull/10837
This PR contains two modifications:
1. support conv3d-bn folding.
2. add some layout in dnnl_json_runtime, and fix some typos.
--
This is an automated message from the Apache Git Service.
T
crazydemo opened a new pull request #10836:
URL: https://github.com/apache/tvm/pull/10836
This PR aims to enhance the `GetRootCall` function to support various
topology.
The original `GetRootCall` only supports dnnl_pattern like
`add(add(conv(data, weight), bias), sum_data)`.
But
crazydemo opened a new pull request #10835:
URL: https://github.com/apache/tvm/pull/10835
This PR is inspired by `tensorrt.py`.
It aims to add `prune` function to `dnnl subgraphs`, so that we can only
keep partitions contain compute-intensive ops, and offload some useless
partitions
areusch commented on a change in pull request #65:
URL: https://github.com/apache/tvm-rfcs/pull/65#discussion_r839120089
##
File path: rfcs/0009_Unified_Static_Memory_Planning.md
##
@@ -515,4 +663,6 @@ NOTE : to support tir.constants generally, we'll be
enhancing the bound rel
AndrewZhaoLuo opened a new pull request #10834:
URL: https://github.com/apache/tvm/pull/10834
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 review
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 642fc57 [Metaschedule] Add demonstration of selectively tuning relay
ops with TIR schedules (#10793)
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 10f037f [ci][docker] Remove nvidia ml repository before updating
(#10828)
add 72c761c [MetaSchedule] Fine-Grain
junrushao1994 merged pull request #10823:
URL: https://github.com/apache/tvm/pull/10823
--
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-un
junrushao1994 commented on pull request #10823:
URL: https://github.com/apache/tvm/pull/10823#issuecomment-1083810697
Noce!
--
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.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 897019d [Pass][Bugfix] Disable re-use of non-flat buffers in
StorageRewrite. (#10787)
add 642fc57 [
vinx13 commented on issue #10831:
URL: https://github.com/apache/tvm/issues/10831#issuecomment-1083762983
The script with local variables is indeed parsed correctly. There are some
issues in `CompactBufferRegion`. When the upper loop is present, the shape of
`C_reg` will be the union of ac
driazati opened a new pull request #10833:
URL: https://github.com/apache/tvm/pull/10833
This implements
https://discuss.tvm.apache.org/t/rfc-allow-merging-via-pr-comments/12220. The
bot can be invoked from a top-level review comment or via a regular PR comment.
The text `@tvm-bot merge`
altanh commented on issue #10831:
URL: https://github.com/apache/tvm/issues/10831#issuecomment-1083748600
> Thanks @altanh for reporting this. Unfortunately, defining local variables
in tvm script is not supported now
Is something happening when I remove the upper loop in that case?
driazati opened a new issue #10832:
URL: https://github.com/apache/tvm/issues/10832
Seen it in many places e.g.
https://ci.tlcpack.ai/blue/organizations/jenkins/docker-images-ci%2Fdaily-docker-image-rebuild/detail/daily-docker-image-rebuild/274/pipeline/57
--
This is an automated message
vinx13 commented on issue #10831:
URL: https://github.com/apache/tvm/issues/10831#issuecomment-1083742362
Thanks @altanh for reporting this. Unfortunately, defining local variables
in tvm script is not supported now
--
This is an automated message from the Apache Git Service.
To respond
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 de93d81 [skip ci][hotfix] Fix broken lint (#10827)
add b5cad84 [TE] Correctly generate buffer binds
zxybazh commented on pull request #10823:
URL: https://github.com/apache/tvm/pull/10823#issuecomment-1083713689
@junrushao1994 CI passed and issues addressed!
--
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
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 b2a0e1d [CUBLAS] Add cuBLAS as a Relay partitioning target (BYOC)
(#10820)
add 6d42264 bump PyTorch
altanh commented on issue #10831:
URL: https://github.com/apache/tvm/issues/10831#issuecomment-1083694916
I should note that removing the upper loop
```
for rii, rjj in T.grid(8, 8):
C_reg[rii, rjj] = T.float32(0)
```
seems to get rid of the error. The specific variable na
jwfromm commented on a change in pull request #10722:
URL: https://github.com/apache/tvm/pull/10722#discussion_r839009864
##
File path: python/tvm/driver/tvmc/model.py
##
@@ -281,7 +320,9 @@ def export_package(
if output_format == "mlf" and cross:
raise TV
masahi commented on a change in pull request #10689:
URL: https://github.com/apache/tvm/pull/10689#discussion_r839015309
##
File path: src/tir/schedule/primitive/sampling.cc
##
@@ -299,22 +299,12 @@ std::vector
SamplePerfectTile(support::LinearCongruentialEngine::TRandS
r
zxybazh commented on a change in pull request #10689:
URL: https://github.com/apache/tvm/pull/10689#discussion_r839012913
##
File path: src/tir/schedule/primitive/sampling.cc
##
@@ -299,22 +299,12 @@ std::vector
SamplePerfectTile(support::LinearCongruentialEngine::TRandS
zxybazh commented on pull request #10366:
URL: https://github.com/apache/tvm/pull/10366#issuecomment-1083687484
Hey Junru, the changes of API looks reasonable to me. Would you please
retrigger the CI?
--
This is an automated message from the Apache Git Service.
To respond to the message,
altanh opened a new issue #10831:
URL: https://github.com/apache/tvm/issues/10831
### Expected behavior
The code should build.
### Actual behavior
TVM complains about undefined variables, when there are none.
### Environment
Reproduced on main.
### S
kparzysz-quic opened a new pull request #10830:
URL: https://github.com/apache/tvm/pull/10830
There is no way to pass `kwargs` dictionary from C++ code, so the previous
way never worked. Use TVM's `Map` instead, and pass the target architecture
version to the linker to use libraries specif
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 fb49a99 [ETHOSN] int8 support for the mean operator (#10463)
add b2a0e1d [CUBLAS] Add cuBLAS as a Re
kparzysz-quic opened a new pull request #10829:
URL: https://github.com/apache/tvm/pull/10829
There are a few tweaks that are needed related to directorystructure in the
SDK.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub a
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 642fc57 [Metaschedule] Add demonstration of selectively tuning relay
ops with TIR schedules (#10793)
add 10f037f
masahi merged pull request #10828:
URL: https://github.com/apache/tvm/pull/10828
--
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.
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 897019d [Pass][Bugfix] Disable re-use of non-flat buffers in
StorageRewrite. (#10787)
add 642fc57 [Metaschedule
junrushao1994 merged pull request #10793:
URL: https://github.com/apache/tvm/pull/10793
--
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-un
junrushao1994 commented on pull request #10793:
URL: https://github.com/apache/tvm/pull/10793#issuecomment-1083594771
Thanks @masahi @jwfromm for the discussion, and @shingjan @vinx13 for
review! I'm going to merge it in
--
This is an automated message from the Apache Git Service.
To res
junrushao1994 commented on a change in pull request #10793:
URL: https://github.com/apache/tvm/pull/10793#discussion_r838937818
##
File path: tests/python/unittest/test_meta_schedule_tune_relay.py
##
@@ -323,6 +325,222 @@ def get_output(data, lib):
assert np.allclose(a
mbs-octoml commented on a change in pull request #10826:
URL: https://github.com/apache/tvm/pull/10826#discussion_r838913408
##
File path: python/tvm/relay/op/contrib/cublas.py
##
@@ -156,3 +165,21 @@ def _lower_matmul(op: relay.Call, inputs: List[te.Tensor])
-> te.Tensor:
This is an automated email from the ASF dual-hosted git repository.
masahi 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 897019d [Pass][Bugfix] Disable re-use of non-flat buff
masahi merged pull request #10787:
URL: https://github.com/apache/tvm/pull/10787
--
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.
This is an automated email from the ASF dual-hosted git repository.
masahi 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 b5cad84 [TE] Correctly generate buffer binds with axis
masahi merged pull request #10819:
URL: https://github.com/apache/tvm/pull/10819
--
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.
driazati opened a new pull request #10828:
URL: https://github.com/apache/tvm/pull/10828
`bash docker/build.sh ci_gpu` fails locally as well as in CI:
https://ci.tlcpack.ai/blue/organizations/jenkins/docker-images-ci%2Fdaily-docker-image-rebuild/detail/daily-docker-image-rebuild/273/pipelin
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 6d42264 bump PyTorch version to 1.11 (#10794)
add de93d81 [skip ci][hotfix] Fix broken lint (#10827)
No new revisi
masahi merged pull request #10827:
URL: https://github.com/apache/tvm/pull/10827
--
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.
driazati removed a comment on pull request #10794:
URL: https://github.com/apache/tvm/pull/10794#issuecomment-1083533795
I started a manual build so we don't have to wait:
https://ci.tlcpack.ai/job/docker-images-ci/job/daily-docker-image-rebuild/272/
Usually takes about an hour
--
driazati commented on pull request #10794:
URL: https://github.com/apache/tvm/pull/10794#issuecomment-1083533795
I started a manual build so we don't have to wait:
https://ci.tlcpack.ai/job/docker-images-ci/job/daily-docker-image-rebuild/272/
Usually takes about an hour
--
This is
masahi commented on pull request #10794:
URL: https://github.com/apache/tvm/pull/10794#issuecomment-1083531778
Yes, the next step is to wait until the nightly image appears in
https://hub.docker.com/r/tlcpackstaging/ci_gpu/tags. It will happen about 12h
later.
--
This is an automated me
driazati opened a new pull request #10827:
URL: https://github.com/apache/tvm/pull/10827
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
t-vi commented on pull request #10794:
URL: https://github.com/apache/tvm/pull/10794#issuecomment-1083527546
Thank you, @masahi for merging and helping me. So next we would need to
update the docker gpu image used before I can return to enabling the test that
needs PyTorch 1.11?
--
This
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 b2a0e1d [CUBLAS] Add cuBLAS as a Relay partitioning target (BYOC)
(#10820)
add 6d42264 bump PyTorch version to 1.1
masahi merged pull request #10794:
URL: https://github.com/apache/tvm/pull/10794
--
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.
mbaret commented on pull request #10826:
URL: https://github.com/apache/tvm/pull/10826#issuecomment-1083476419
cc @mbs-octoml @mikepapadim
--
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 sp
This is an automated email from the ASF dual-hosted git repository.
mbrookhart pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from fb49a99 [ETHOSN] int8 support for the mean operator (#10463)
add b2a0e1d [CUBLAS] Add cuBLAS as a Relay partiti
mbrookhart commented on pull request #10820:
URL: https://github.com/apache/tvm/pull/10820#issuecomment-1083471236
Thanks @mbaret @mbs-octoml @mikepapadim
--
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
mbrookhart merged pull request #10820:
URL: https://github.com/apache/tvm/pull/10820
--
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-unsub
mbaret opened a new pull request #10826:
URL: https://github.com/apache/tvm/pull/10826
Currently on top of https://github.com/apache/tvm/pull/10820 so contains
those changes too. Will be rebased when that PR is merged.
Add support for nn.dense and nn.batch_matmul using cuBLAS. This c
shukun-ziqiangxu commented on pull request #10504:
URL: https://github.com/apache/tvm/pull/10504#issuecomment-1083346807
Hi, @gromero
Sorry to bother you again. I have fixed all errors except the docs:GPU
warning "Inline interpreted text or phrase reference start-string without
en
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 8fddcc1 [ETHOSN] int8 support for tanh operator (#10813)
add fb49a99 [ETHOSN] int8 support for the m
driazati opened a new pull request #10825:
URL: https://github.com/apache/tvm/pull/10825
This adds a timestamp to the generated Jenkinsfile that is ignored when
`--check`-ing. This line should generate merge conflicts for updates that would
not pass `--check` in CI on main, so PRs will nee
pfk-beta commented on pull request #10222:
URL: https://github.com/apache/tvm/pull/10222#issuecomment-1083250343
@areusch thanks for reply. I'll try to change it this or next week according
to your suggestions :)
--
This is an automated message from the Apache Git Service.
To respond to
pfk-beta edited a comment on pull request #10222:
URL: https://github.com/apache/tvm/pull/10222#issuecomment-1083250343
@areusch thanks for reply. I'll try to make changes this or next week
according to your suggestions :)
--
This is an automated message from the Apache Git Service.
To r
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 d0c7c78 [microNPU] Tweak a layout transform matrix (#10763)
add 8fddcc1 [ETHOSN] int8 support for ta
tqchen commented on pull request #10816:
URL: https://github.com/apache/tvm/pull/10816#issuecomment-1083217149
Thank you @Lunderberg ! yes love all the discussions so far
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and us
lhutton1 commented on a change in pull request #10801:
URL: https://github.com/apache/tvm/pull/10801#discussion_r838490715
##
File path: python/tvm/relay/op/contrib/arm_compute_lib.py
##
@@ -286,6 +286,7 @@ def _func_wrapper(expr):
_register_external_op_helper("reshape")
+
Lunderberg commented on pull request #10819:
URL: https://github.com/apache/tvm/pull/10819#issuecomment-1083184272
One failing unit test, due to HTTP error. Bumping CI to restart.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to Git
Lunderberg commented on pull request #10816:
URL: https://github.com/apache/tvm/pull/10816#issuecomment-1083179609
Thank you, and I agree that this type of change requires a larger
discussion. My intent was for this draft PR to be an option in that
discussion, not a ready-to-merge change
mikepapadim commented on pull request #10820:
URL: https://github.com/apache/tvm/pull/10820#issuecomment-1083172228
thanks @mbaret LGTM
--
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 specif
t-vi commented on pull request #10794:
URL: https://github.com/apache/tvm/pull/10794#issuecomment-1083172495
All green. :slightly_smiling_face:
--
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 t
Lunderberg commented on pull request #10787:
URL: https://github.com/apache/tvm/pull/10787#issuecomment-1083160155
Passed CI, but needed to rebase on main to resolve conflict with #10788
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on
mbaret commented on pull request #10820:
URL: https://github.com/apache/tvm/pull/10820#issuecomment-1083151920
Thanks @mbs-octoml, I've refactored both the 'lower funcs' and tests to
extract all the boilerplate into reusable code. I've also switched to first
using create_prim_func, then I
This is an automated email from the ASF dual-hosted git repository.
mousius 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 fb49a99 [ETHOSN] int8 support for the mean operator (
Mousius merged pull request #10463:
URL: https://github.com/apache/tvm/pull/10463
--
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
Mousius commented on a change in pull request #10463:
URL: https://github.com/apache/tvm/pull/10463#discussion_r838513266
##
File path: tests/python/contrib/test_ethosn/test_mean.py
##
@@ -40,18 +41,22 @@ def _get_model(shape, axis, keepdims, input_zp, input_sc,
output_zp, out
ekalda commented on a change in pull request #10510:
URL: https://github.com/apache/tvm/pull/10510#discussion_r838511632
##
File path: python/tvm/contrib/ethosu/cascader/device_config.py
##
@@ -492,29 +492,31 @@ def get_elementwise_block_config(
banks_available -=
Leo-arm commented on a change in pull request #10463:
URL: https://github.com/apache/tvm/pull/10463#discussion_r838462817
##
File path: tests/python/contrib/test_ethosn/test_mean.py
##
@@ -40,18 +41,22 @@ def _get_model(shape, axis, keepdims, input_zp, input_sc,
output_zp, out
ekalda commented on pull request #10824:
URL: https://github.com/apache/tvm/pull/10824#issuecomment-1083055288
@lhutton1 @manupa-arm @NicolaLancellotti an unglamorous refactor :)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to Git
1 - 100 of 114 matches
Mail list logo