[GitHub] [tvm] driazati merged pull request #12597: [DOC] fix code-block error in debuggging TVM part.

driazati merged PR #12597: URL: https://github.com/apache/tvm/pull/12597 -- 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:

[tvm] branch main updated (cc19cdd711 -> 56b7c8ae96)

This is an automated email from the ASF dual-hosted git repository. driazati pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from cc19cdd711 [microTVM][Zephyr] Add recommended heap size for NRF and qemu_x86 (#12585) add 56b7c8ae96 [CI] Assert

[GitHub] [tvm] driazati merged pull request #12436: [CI] Assert some unittests are not skipped in CI

driazati merged PR #12436: URL: https://github.com/apache/tvm/pull/12436 -- 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:

[GitHub] [tvm] csullivan commented on a diff in pull request #12411: [Hexagon] Asynchronous DMA support

csullivan commented on code in PR #12411: URL: https://github.com/apache/tvm/pull/12411#discussion_r955115733 ## tests/cpp-runtime/hexagon/ring_buffer_tests.cc: ## @@ -0,0 +1,109 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor

[GitHub] [tvm] cconvey opened a new issue, #12602: [CI Problem] [Checks API] No suitable checks publisher found.

cconvey opened a new issue, #12602: URL: https://github.com/apache/tvm/issues/12602 ### Branch/PR Failing https://github.com/apache/tvm/commit/1afd0593956066635ee49297b731726c9218c91c ### Jenkins Link

[GitHub] [tvm] cconvey opened a new issue, #12601: [CI Problem] maven failed download of Linux tvm4j

cconvey opened a new issue, #12601: URL: https://github.com/apache/tvm/issues/12601 Note: I'm may not be correctly interpreting the error output, so this issue's title might need updating ### Branch/PR Failing

[GitHub] [tvm] cconvey opened a new issue, #12600: [CI Problem] failed docs push to https://github.com/apache/tvm-site.git

cconvey opened a new issue, #12600: URL: https://github.com/apache/tvm/issues/12600 ### Branch/PR Failing https://github.com/apache/tvm/commit/5cef6bf559265e74b84504ed2e190f29f5c5bf33 https://github.com/apache/tvm/commit/13ebbfb37f8cec1da71d88fbcbecdd4ad4d24dcc ### Jenkins

[GitHub] [tvm] cconvey opened a new issue, #12599: [CI Problem] A problem occurred configuring root project 'android_rpc'.

cconvey opened a new issue, #12599: URL: https://github.com/apache/tvm/issues/12599 Possibly related: another `android_rpc` failure from several weeks ago: https://github.com/apache/tvm/issues/12191 ### Branch/PR Failing

[GitHub] [tvm] leandron opened a new pull request, #12598: [COMMUNITY] @cconvey -> Reviewer

leandron opened a new pull request, #12598: URL: https://github.com/apache/tvm/pull/12598 Please join me in welcoming Christian Convey (@cconvey) as a new reviewer in TVM. Christian has been involved in building TVM’s hexagon backend, building robust testing infrastructure and contributing

[GitHub] [tvm] cconvey commented on issue #12511: [Flaky Test] various tests in `tests/python/contrib/test_ethosu/test_codegen.py`

cconvey commented on issue #12511: URL: https://github.com/apache/tvm/issues/12511#issuecomment-1227359596 Just FYI, another occurrence of this CI failure occurred _before_ the bugfix landed on `main`: https://ci.tlcpack.ai/blue/organizations/jenkins/tvm/detail/main/4137/pipeline --

[tvm] branch main updated: [microTVM][Zephyr] Add recommended heap size for NRF and qemu_x86 (#12585)

This is an automated email from the ASF dual-hosted git repository. mehrdadh 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 cc19cdd711 [microTVM][Zephyr] Add recommended heap

[GitHub] [tvm] mehrdadh merged pull request #12585: [microTVM][Zephyr] Add recommended heap size for NRF and qemu_x86

mehrdadh merged PR #12585: URL: https://github.com/apache/tvm/pull/12585 -- 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:

[GitHub] [tvm] huanmei9 opened a new pull request, #12597: [DOC] fix code-block error in debuggging TVM part.

huanmei9 opened a new pull request, #12597: URL: https://github.com/apache/tvm/pull/12597 The code block in part Debuggging TVM is not showing up. Just fix it. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[tvm] branch last-successful updated (9aac161a46 -> 40bdea8d7a)

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 9aac161a46 [MetaSchedule] Add software pipeline in CUDA tensor core auto tensorization (#12544) add

[GitHub] [tvm] wzh99 opened a new pull request, #12596: [TOPI][Bugfix] Make semantics of empty `axis` in `squeeze` consistent with Relay

wzh99 opened a new pull request, #12596: URL: https://github.com/apache/tvm/pull/12596 This PR fixes #11697. The analysis of the bug is elaborated in #12400. The key problem is whether `axis` in `squeeze` means doing nothing or squeezing all one-dimensional axes. In #12400, I

[GitHub] [tvm] Theoo1997 opened a new issue, #12595: [Bug] graph_mod = tvm.micro.create_local_graph_executor() Error

Theoo1997 opened a new issue, #12595: URL: https://github.com/apache/tvm/issues/12595 Hi, I am trying to execute int8 tf lite models on x86 (my local PC). So I've used micro TVM and specifically the

[GitHub] [tvm] masahi merged pull request #12592: [CI] Install xgboost in Hexagon image

masahi merged PR #12592: URL: https://github.com/apache/tvm/pull/12592 -- 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:

[tvm] branch main updated (40bdea8d7a -> fb7cf97fbc)

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 40bdea8d7a [PyTorch] Add aten::new_empty (#12591) add fb7cf97fbc [CI] Install xgboost in Hexagon image (#12592) No

[GitHub] [tvm] wrongtest-intellif commented on a diff in pull request #12581: [CUDA][CodeGen] Fix cuda codegen's fp16 inf literal

wrongtest-intellif commented on code in PR #12581: URL: https://github.com/apache/tvm/pull/12581#discussion_r954791246 ## src/target/source/codegen_cuda.cc: ## @@ -1197,8 +1197,10 @@ inline void PrintConst(const FloatImmNode* op, std::ostream& os, CodeGenCUDA* p) break;

[GitHub] [tvm] NicolaLancellotti commented on pull request #12594: [ETHOSN] Improve inferring new shape of the Reshape operator

NicolaLancellotti commented on PR #12594: URL: https://github.com/apache/tvm/pull/12594#issuecomment-1227071859 @lhutton1 @leandron -- 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

[GitHub] [tvm] NicolaLancellotti opened a new pull request, #12594: [ETHOSN] Improve inferring new shape of the Reshape operator

NicolaLancellotti opened a new pull request, #12594: URL: https://github.com/apache/tvm/pull/12594 This pr improves the inference of the new shape of the Reshape operator for the Arm(R) Ethos(TM)-N NPU. -- This is an automated message from the Apache Git Service. To respond to the

[tvm] branch main updated (b38738434b -> 40bdea8d7a)

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 b38738434b [TIR] Expose WMMA-related TensorCore builtins (#12589) add 40bdea8d7a [PyTorch] Add aten::new_empty

[GitHub] [tvm] masahi merged pull request #12591: [PyTorch] Add aten::new_empty

masahi merged PR #12591: URL: https://github.com/apache/tvm/pull/12591 -- 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:

[GitHub] [tvm] masahi merged pull request #12589: [TIR] Expose WMMA-related TensorCore builtins

masahi merged PR #12589: URL: https://github.com/apache/tvm/pull/12589 -- 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:

[tvm] branch main updated (9aac161a46 -> b38738434b)

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 9aac161a46 [MetaSchedule] Add software pipeline in CUDA tensor core auto tensorization (#12544) add b38738434b [TIR]

[GitHub] [tvm] gigiblender commented on a diff in pull request #12436: [CI] Assert some unittests are not skipped in CI

gigiblender commented on code in PR #12436: URL: https://github.com/apache/tvm/pull/12436#discussion_r954768873 ## tests/python/ci/test_ci.py: ## @@ -33,6 +34,168 @@ def parameterize_named(*values): return pytest.mark.parametrize(",".join(keys), [tuple(d.values()) for d in

[GitHub] [tvm] czh978 opened a new pull request, #12593: [Frontend][TFLite] fix detection_postprocess's non_max_suppression_attrs["force_suppress"]

czh978 opened a new pull request, #12593: URL: https://github.com/apache/tvm/pull/12593 I found the value should be "True" -- 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.

[tvm] branch last-successful updated (cd8fd9121d -> 9aac161a46)

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 cd8fd9121d [TIR] Expose `shift_left` and `shift_right` to Python (#12584) add 9aac161a46

[GitHub] [tvm] lhutton1 commented on pull request #12570: [microNPU] Remove xfail from tests relating to #12511

lhutton1 commented on PR #12570: URL: https://github.com/apache/tvm/pull/12570#issuecomment-1226972904 I took a look at some recent CI runs and it seems these tests are no longer failing -- This is an automated message from the Apache Git Service. To respond to the message, please log on

[GitHub] [tvm] lhutton1 commented on a diff in pull request #12550: [AOT] Add AOTLowerMain pass to lower a Relay main into TIR

lhutton1 commented on code in PR #12550: URL: https://github.com/apache/tvm/pull/12550#discussion_r954666936 ## python/tvm/relay/backend/utils.py: ## @@ -15,6 +15,13 @@ # specific language governing permissions and limitations # under the License. """Utility backend

[GitHub] [tvm] shingjan commented on pull request #12485: [Relay][Op] embedding_bag operator implementation

shingjan commented on PR #12485: URL: https://github.com/apache/tvm/pull/12485#issuecomment-1226898205 I took a quick look and this PR should be in pretty good shape after CI is fixed. cc: @masahi Can you also take a look at this? Would really appreciate your review on this.

[GitHub] [tvm] driazati commented on a diff in pull request #12436: [CI] Assert some unittests are not skipped in CI

driazati commented on code in PR #12436: URL: https://github.com/apache/tvm/pull/12436#discussion_r954601652 ## tests/python/ci/test_ci.py: ## @@ -33,6 +34,168 @@ def parameterize_named(*values): return pytest.mark.parametrize(",".join(keys), [tuple(d.values()) for d in

[GitHub] [tvm] masahi commented on issue #12583: [VOTE] Commit Messages RFC

masahi commented on issue #12583: URL: https://github.com/apache/tvm/issues/12583#issuecomment-1226870601 +1 -- 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

[GitHub] [tvm] sfvaroglu commented on pull request #12577: [F2QI] Fix a rounding error on AvgPool when input and output affine scales differ

sfvaroglu commented on PR #12577: URL: https://github.com/apache/tvm/pull/12577#issuecomment-1226862744 LGTM! Thanks! -- 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

[GitHub] [tvm] masahi closed issue #12590: [Bug] [PyTorch] BatchNorm gives incorrect output with eps=-1.0

masahi closed issue #12590: [Bug] [PyTorch] BatchNorm gives incorrect output with eps=-1.0 URL: https://github.com/apache/tvm/issues/12590 -- 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

[GitHub] [tvm] masahi commented on issue #12590: [Bug] [PyTorch] BatchNorm gives incorrect output with eps=-1.0

masahi commented on issue #12590: URL: https://github.com/apache/tvm/issues/12590#issuecomment-1226857742 I think `eps` is supposed to be a small number. The PyTorch output is all `nan`. -- This is an automated message from the Apache Git Service. To respond to the message, please log on

[GitHub] [tvm] chengven027-intellif commented on pull request #12555: [frontend][onnx]fix pad constant value is none

chengven027-intellif commented on PR #12555: URL: https://github.com/apache/tvm/pull/12555#issuecomment-1226856373 Dose this PR need to be reviewed again? @AndrewZhaoLuo @leandron -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [tvm] masahi opened a new pull request, #12592: [CI] Install xgboost in Hexagon image

masahi opened a new pull request, #12592: URL: https://github.com/apache/tvm/pull/12592 Needed for https://github.com/apache/tvm/pull/12587 -- 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

[tvm] branch main updated: [MetaSchedule] Add software pipeline in CUDA tensor core auto tensorization (#12544)

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 9aac161a46 [MetaSchedule] Add software pipeline in

[GitHub] [tvm] masahi merged pull request #12544: [MetaSchedule] Add software pipeline in CUDA tensor core auto tensorization

masahi merged PR #12544: URL: https://github.com/apache/tvm/pull/12544 -- 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:

[GitHub] [tvm] masahi commented on pull request #12588: [TOPI] Enhance VNNI dot product

masahi commented on PR #12588: URL: https://github.com/apache/tvm/pull/12588#issuecomment-1226830226 Does this yield performance improvement? Would be great if you can also update

<    1   2