[GitHub] [tvm] apivovarov commented on pull request #6740: [Torch] Support bincount and scatter_add ops

apivovarov commented on PR #6740: URL: https://github.com/apache/tvm/pull/6740#issuecomment-1241529764 I'm working on adding TF bincount support. I found that`tf.bincount` internally uses `tf.shape`. But looks like `tf.shape` is not compatible with `relay.vm`. Instead of determining the

[tvm] branch last-successful updated (64031d56d6 -> 89ce171b86)

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 64031d56d6 Move static array initialization into a function go avoid link errors (#12678) add

[GitHub] [tvm] honghuichao commented on issue #12707: [Bug] a bug about fake quantize to intege and split op.

honghuichao commented on issue #12707: URL: https://github.com/apache/tvm/issues/12707#issuecomment-1241451747 @mbrookhart Do you have a plan to modify this pass? If not, I may change another plan to support my schedule. Thanks -- This is an automated message from the Apache Git

[GitHub] [tvm] alter-xp commented on pull request #12644: [ci] Add CSI-NN2 build to Jenkins

alter-xp commented on PR #12644: URL: https://github.com/apache/tvm/pull/12644#issuecomment-1241418100 > I think it's been broken this whole time and just wasn't running, then the fix you made to `make()` actually turned it on. I pushed a commit to disable it so that we can merge this PR

[GitHub] [tvm] alter-xp commented on a diff in pull request #12534: [Docker][CI][RISC-V] Build riscv-isa-sim (spike) in ci_riscv Docker image to enable RISC-V unit testing

alter-xp commented on code in PR #12534: URL: https://github.com/apache/tvm/pull/12534#discussion_r966556760 ## docker/install/ubuntu_download_xuantie_qemu.sh: ## @@ -0,0 +1,56 @@ +#!/bin/bash +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[GitHub] [tvm] jwfromm commented on pull request #12717: [TIR, Schedule] Check consumer in-bound and covered in reverse_compute_inline

jwfromm commented on PR #12717: URL: https://github.com/apache/tvm/pull/12717#issuecomment-1241409641 Thank you @vinx13, this now merged! -- 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 (64031d56d6 -> 89ce171b86)

This is an automated email from the ASF dual-hosted git repository. jwfromm pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 64031d56d6 Move static array initialization into a function go avoid link errors (#12678) add 89ce171b86 [TIR,

[GitHub] [tvm] jwfromm merged pull request #12717: [TIR, Schedule] Check consumer in-bound and covered in reverse_compute_inline

jwfromm merged PR #12717: URL: https://github.com/apache/tvm/pull/12717 -- 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] github-actions[bot] commented on pull request #12744: [ci][docker] Use CMake 3.20.0 for cortexm

github-actions[bot] commented on PR #12744: URL: https://github.com/apache/tvm/pull/12744#issuecomment-1241406209 No additional skipped tests found in this branch for commit 99cb2cd49fe146e066e51c96e843144f086bc3b8. -- This is an automated message from the Apache Git Service. To

[GitHub] [tvm] github-actions[bot] commented on pull request #12744: [ci][docker] Use CMake 3.20.0 for cortexm

github-actions[bot] commented on PR #12744: URL: https://github.com/apache/tvm/pull/12744#issuecomment-1241405912 Built docs for commit 99cb2cd49fe146e066e51c96e843144f086bc3b8 can be found [here](https://pr-docs.tlcpack.ai/PR-12744/2/docs/index.html). -- This is an automated

[GitHub] [tvm] slyubomirsky commented on pull request #12682: [Bugfix][CMake] Update the minimum CMake version to 3.18

slyubomirsky commented on PR #12682: URL: https://github.com/apache/tvm/pull/12682#issuecomment-1241394490 Per [https://github.com/apache/tvm/pull/12744](this PR), should I make the minimum version higher? -- This is an automated message from the Apache Git Service. To respond to the

[tvm] branch last-successful updated (299ca267e7 -> 64031d56d6)

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 299ca267e7 [TIR] Update region min/extent in ReplaceBufferMutator (#12725) add 64031d56d6 Move static

[GitHub] [tvm] PhilippvK commented on pull request #12534: [Docker][CI][RISC-V] Build riscv-isa-sim (spike) in ci_riscv Docker image to enable RISC-V unit testing

PhilippvK commented on PR #12534: URL: https://github.com/apache/tvm/pull/12534#issuecomment-1241359600 > I also intend to do this. Should we also do it in this PR? I added it to this PR. Please check if the changes are okay or if I am missing something @alter-xp. -- This is an

[GitHub] [tvm] driazati opened a new pull request, #12744: [ci][docker] Use CMake 3.20.0 for cortexm

driazati opened a new pull request, #12744: URL: https://github.com/apache/tvm/pull/12744 The Zephyr project builds require 3.20.0 to work correctly -- 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

[GitHub] [tvm] gromero commented on issue #12743: [VOTE] Issue Triage Workflow RFC

gromero commented on issue #12743: URL: https://github.com/apache/tvm/issues/12743#issuecomment-1241311328 +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-rfcs] gromero commented on a diff in pull request #93: Issue Triage Workflow RFC

gromero commented on code in PR #93: URL: https://github.com/apache/tvm-rfcs/pull/93#discussion_r966469043 ## rfcs/0093_Issue_Triage.md: ## @@ -0,0 +1,309 @@ +# Issue Triage + +* Feature Name: `Update Issue Triage Workflow` +* Co-authored with @areusch, @denise + +# **Summary**

[GitHub] [tvm] vinx13 commented on issue #12743: [VOTE] Issue Triage Workflow RFC

vinx13 commented on issue #12743: URL: https://github.com/apache/tvm/issues/12743#issuecomment-1241307038 +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

[tvm] branch main updated (299ca267e7 -> 64031d56d6)

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 299ca267e7 [TIR] Update region min/extent in ReplaceBufferMutator (#12725) add 64031d56d6 Move static array

[GitHub] [tvm] vinx13 merged pull request #12678: Move static array initialization into a function go avoid link errors

vinx13 merged PR #12678: URL: https://github.com/apache/tvm/pull/12678 -- 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] janetsc commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

janetsc commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966454458 ## src/runtime/hexagon/hexagon_device_api.h: ## @@ -45,11 +45,27 @@ class HexagonDeviceAPI final : public DeviceAPI { static HexagonDeviceAPI* Global(); //!

[GitHub] [tvm] leandron commented on issue #12743: [VOTE] Issue Triage Workflow RFC

leandron commented on issue #12743: URL: https://github.com/apache/tvm/issues/12743#issuecomment-1241271856 +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] driazati commented on issue #12743: [VOTE] Issue Triage Workflow RFC

driazati commented on issue #12743: URL: https://github.com/apache/tvm/issues/12743#issuecomment-1241264017 +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] tkonolige commented on issue #12743: [VOTE] Issue Triage Workflow RFC

tkonolige commented on issue #12743: URL: https://github.com/apache/tvm/issues/12743#issuecomment-1241259282 +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] JosephTheOctonaut commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

JosephTheOctonaut commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966436276 ## src/runtime/hexagon/hexagon_device_api.h: ## @@ -45,11 +45,27 @@ class HexagonDeviceAPI final : public DeviceAPI { static HexagonDeviceAPI* Global();

[GitHub] [tvm] JosephTheOctonaut commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

JosephTheOctonaut commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966434334 ## src/runtime/hexagon/hexagon_device_api.h: ## @@ -45,11 +45,27 @@ class HexagonDeviceAPI final : public DeviceAPI { static HexagonDeviceAPI* Global();

[GitHub] [tvm] janetsc commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

janetsc commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966431706 ## src/runtime/hexagon/hexagon_device_api.h: ## @@ -45,11 +45,27 @@ class HexagonDeviceAPI final : public DeviceAPI { static HexagonDeviceAPI* Global(); //!

[GitHub] [tvm] janetsc commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

janetsc commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966430790 ## src/runtime/hexagon/hexagon_device_api.h: ## @@ -45,11 +45,27 @@ class HexagonDeviceAPI final : public DeviceAPI { static HexagonDeviceAPI* Global(); //!

[GitHub] [tvm] areusch opened a new issue, #12743: [VOTE] Issue Triage Workflow RFC

areusch opened a new issue, #12743: URL: https://github.com/apache/tvm/issues/12743 This is a formal vote thread to determine committer and PMC support for https://github.com/apache/tvm-rfcs/pull/93. Replying +1 here means you support the RFC and we should merge it. This vote thread is due

[GitHub] [tvm] areusch opened a new issue, #12742: [Bug] deprecation warning when using tvmc compile with BYOC targets

areusch opened a new issue, #12742: URL: https://github.com/apache/tvm/issues/12742 See https://discuss.tvm.apache.org/t/how-to-get-rid-of-deprecated-target-warning-for-marvell-hybrid-target/13497. ``` $python3 -m pdb -m tvm.driver.tvmc compile --target="mrvl, llvm"

[GitHub] [tvm] JosephTheOctonaut commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

JosephTheOctonaut commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966412900 ## src/runtime/hexagon/hexagon_device_api.h: ## @@ -45,11 +45,27 @@ class HexagonDeviceAPI final : public DeviceAPI { static HexagonDeviceAPI* Global();

[GitHub] [tvm] jwfromm commented on a diff in pull request #12717: [TIR, Schedule] Check consumer in-bound and covered in reverse_compute_inline

jwfromm commented on code in PR #12717: URL: https://github.com/apache/tvm/pull/12717#discussion_r966384283 ## src/tir/schedule/primitive/compute_inline.cc: ## @@ -571,6 +596,34 @@ class ReverseComputeInliner : public BaseInliner { using BaseInliner::VisitExpr_; using

[GitHub] [tvm] jwfromm commented on a diff in pull request #12717: [TIR, Schedule] Check consumer in-bound and covered in reverse_compute_inline

jwfromm commented on code in PR #12717: URL: https://github.com/apache/tvm/pull/12717#discussion_r966383754 ## tests/python/unittest/test_tir_schedule_compute_inline.py: ## @@ -822,5 +848,15 @@ def test_compute_inline_opaque_access_with_tvm_access_ptr(use_block_name): )

[GitHub] [tvm] github-actions[bot] commented on pull request #11893: [ci][docker] Run build/test with Docker changes

github-actions[bot] commented on PR #11893: URL: https://github.com/apache/tvm/pull/11893#issuecomment-1241140555 The list below shows some tests that ran in main 299ca267e7641b5fa6e78dd131d0574e310f9a13 but were skipped in the CI build of 625bde0d6cf886edf8474ac44be102634518d687:

[GitHub] [tvm] Lunderberg commented on pull request #12662: [Hexagon] Validate 2-d physical shapes for TIR-derived schedules

Lunderberg commented on PR #12662: URL: https://github.com/apache/tvm/pull/12662#issuecomment-1241118855 After rebasing onto main, with the fix applied in #12652, all tests are passing. -- This is an automated message from the Apache Git Service. To respond to the message, please log on

[GitHub] [tvm] tkonolige commented on a diff in pull request #11358: [Virtual Machine] Implementation of 'set_output_zero_copy'

tkonolige commented on code in PR #11358: URL: https://github.com/apache/tvm/pull/11358#discussion_r966291114 ## include/tvm/runtime/vm/vm.h: ## @@ -339,6 +371,51 @@ class TVM_DLL VirtualMachine : public runtime::ModuleNode { void SetInputTensorWithIndex(std::vector&

[tvm] branch last-successful updated (b2bd434ef9 -> 299ca267e7)

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 b2bd434ef9 [TIR] Handle axis_separators during FlattenBuffer (#12652) add 299ca267e7 [TIR] Update

[GitHub] [tvm] mehrdadh opened a new pull request, #12741: [microtvm][Zephyr] Add project overlay to overwrite device tree configs

mehrdadh opened a new pull request, #12741: URL: https://github.com/apache/tvm/pull/12741 This PR adds a mechanism to overwrite device tree configs in zephyr project. It also adds an overlay for nucleo_l4r5zi board to change processor frequency from 80MHz which is the default to 120MHz.

[GitHub] [tvm] trahman-quic commented on pull request #12606: [TOPI][Hexagon] Implement quantized elementwise for hexagon

trahman-quic commented on PR #12606: URL: https://github.com/apache/tvm/pull/12606#issuecomment-1241049333 > Thanks for the PR, Tasmia! It looks good to me. Thank you @jverma-quic . @kparzysz-quic @mehrdadh, please let me know if it looks good to merge now. Thanks -- This is

[GitHub] [tvm] driazati commented on pull request #12740: [testing][do not review] test CI for PR #11893

driazati commented on PR #12740: URL: https://github.com/apache/tvm/pull/12740#issuecomment-1241048258 @tvm-bot rerun -- 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] trahman-quic commented on a diff in pull request #12606: [TOPI][Hexagon] Implement quantized elementwise for hexagon

trahman-quic commented on code in PR #12606: URL: https://github.com/apache/tvm/pull/12606#discussion_r966158192 ## python/tvm/topi/hexagon/qnn/qadd_qsub_qmul.py: ## @@ -0,0 +1,270 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license

[tvm] branch last-successful updated (ed630122c2 -> b2bd434ef9)

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 ed630122c2 [Test] Add tvm.testing.requires_libtorch (#12737) add b2bd434ef9 [TIR] Handle

[GitHub] [tvm] valmat07 commented on a diff in pull request #12490: [OpenCL] Enable OpenCL for GPU tests

valmat07 commented on code in PR #12490: URL: https://github.com/apache/tvm/pull/12490#discussion_r966238113 ## tests/scripts/task_python_integration.sh: ## @@ -61,12 +61,14 @@ run_pytest cython ${TVM_INTEGRATION_TESTSUITE_NAME}-dso_plugin_module-1 apps/dso run_pytest ctypes

[GitHub] [tvm] driazati closed issue #12089: [CI Image] Updates to ci_cpu and ci_qemu to reflect CMSIS-NN SHA upgrade

driazati closed issue #12089: [CI Image] Updates to ci_cpu and ci_qemu to reflect CMSIS-NN SHA upgrade URL: https://github.com/apache/tvm/issues/12089 -- 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

[GitHub] [tvm] driazati commented on issue #12089: [CI Image] Updates to ci_cpu and ci_qemu to reflect CMSIS-NN SHA upgrade

driazati commented on issue #12089: URL: https://github.com/apache/tvm/issues/12089#issuecomment-1241000576 Closing since the images are currently on fae79bbc3e499f3b9f26c9a13743896f948b723d which should include the relevant PR here. Please re-open if this is not the case -- This is an

[GitHub] [tvm] leandron commented on issue #12089: [CI Image] Updates to ci_cpu and ci_qemu to reflect CMSIS-NN SHA upgrade

leandron commented on issue #12089: URL: https://github.com/apache/tvm/issues/12089#issuecomment-1240997094 Just checking whether this ticket can be closed, please update. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] driazati commented on pull request #12644: [ci] Add CSI-NN2 build to Jenkins

driazati commented on PR #12644: URL: https://github.com/apache/tvm/pull/12644#issuecomment-1240996693 > hi @areusch @driazati, CI for build GPU failed, which seems to be because of what I added about `--build_dir`. The GPU has two build scripts. The code shows that they are compiled in

[tvm] branch csinn_jenkins updated (9e57408c4d -> 767b96f874)

This is an automated email from the ASF dual-hosted git repository. driazati pushed a change to branch csinn_jenkins in repository https://gitbox.apache.org/repos/asf/tvm.git from 9e57408c4d [ci] Add CSI-NN2 build to Jenkins add 767b96f874 Disable GPU other build No new revisions were

[GitHub] [tvm] leandron commented on issue #9705: [CI Problem] CI node out of memory

leandron commented on issue #9705: URL: https://github.com/apache/tvm/issues/9705#issuecomment-1240995754 Cleaning up old tickets that are solved, so I'm closing this one. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] leandron closed issue #9705: [CI Problem] CI node out of memory

leandron closed issue #9705: [CI Problem] CI node out of memory URL: https://github.com/apache/tvm/issues/9705 -- 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,

[GitHub] [tvm] driazati opened a new issue, #12739: [ci] Re-enable GPU other build

driazati opened a new issue, #12739: URL: https://github.com/apache/tvm/issues/12739 See #12644 for context -- 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,

[GitHub] [tvm] leandron closed issue #11733: [CI Image] Update Lint image

leandron closed issue #11733: [CI Image] Update Lint image URL: https://github.com/apache/tvm/issues/11733 -- 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,

[GitHub] [tvm] leandron commented on issue #11733: [CI Image] Update Lint image

leandron commented on issue #11733: URL: https://github.com/apache/tvm/issues/11733#issuecomment-1240994081 This seems to be done from a long time, given at the moment ci-lint is `20220810-060142-fae79bbc3`, so closing the issue. -- This is an automated message from the Apache Git

[GitHub] [tvm] leandron commented on issue #12573: [CI Image] Remove Vela from ci_cpu

leandron commented on issue #12573: URL: https://github.com/apache/tvm/issues/12573#issuecomment-1240991566 This is being dealt with in the context of https://github.com/apache/tvm/pull/12738 -- This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [tvm] driazati commented on a diff in pull request #12490: [OpenCL] Enable OpenCL for GPU tests

driazati commented on code in PR #12490: URL: https://github.com/apache/tvm/pull/12490#discussion_r966214352 ## tests/python/contrib/test_opencl/test_run_gtests.py: ## @@ -28,6 +28,7 @@ # for example to run all "foo" tests twice and observe gtest output run # pytest -sv

[GitHub] [tvm] driazati commented on a diff in pull request #12490: [OpenCL] Enable OpenCL for GPU tests

driazati commented on code in PR #12490: URL: https://github.com/apache/tvm/pull/12490#discussion_r966213489 ## tests/scripts/task_python_integration.sh: ## @@ -61,12 +61,14 @@ run_pytest cython ${TVM_INTEGRATION_TESTSUITE_NAME}-dso_plugin_module-1 apps/dso run_pytest ctypes

[GitHub] [tvm] driazati commented on pull request #12729: Upgrade onnx, onnxruntime, onnxoptimizer

driazati commented on PR #12729: URL: https://github.com/apache/tvm/pull/12729#issuecomment-1240985593 Currently there's no good solution outside of running things locally, in the past for these kinds of changes it's been more of a merge it first, build new Docker images, then test the

[GitHub] [tvm] Lunderberg commented on pull request #12691: [Runtime][Bugfix] Added type-checking for Array::insert

Lunderberg commented on PR #12691: URL: https://github.com/apache/tvm/pull/12691#issuecomment-1240983513 Sounds reasonable, and I've added a comment weighing in on that thread. If it becomes a sticking point on this PR, I can rewrite to avoid C++17, but C++17 has enough benefits that it

[GitHub] [tvm] mehrdadh commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

mehrdadh commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966187693 ## python/tvm/contrib/hexagon/build.py: ## @@ -149,6 +149,18 @@ def stop_server(self): """Stop the RPC server""" ... +def

[GitHub] [tvm] Lunderberg commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

Lunderberg commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966186207 ## python/tvm/contrib/hexagon/build.py: ## @@ -149,6 +149,18 @@ def stop_server(self): """Stop the RPC server""" ... +def

[GitHub] [tvm] mehrdadh commented on a diff in pull request #12727: [Hexagon] [runtime] Improve runtime resource management

mehrdadh commented on code in PR #12727: URL: https://github.com/apache/tvm/pull/12727#discussion_r966186024 ## python/tvm/contrib/hexagon/build.py: ## @@ -149,6 +149,18 @@ def stop_server(self): """Stop the RPC server""" ... +def

[tvm] branch main updated: [TIR] Update region min/extent in ReplaceBufferMutator (#12725)

This is an automated email from the ASF dual-hosted git repository. lunderberg 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 299ca267e7 [TIR] Update region min/extent in

[GitHub] [tvm] Lunderberg merged pull request #12725: [TIR] Update region min/extent in ReplaceBufferMutator

Lunderberg merged PR #12725: URL: https://github.com/apache/tvm/pull/12725 -- 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 update_docker_tf291 updated (1a94c9224f -> d09d32e849)

This is an automated email from the ASF dual-hosted git repository. leandron pushed a change to branch update_docker_tf291 in repository https://gitbox.apache.org/repos/asf/tvm.git discard 1a94c9224f [CI] Update Docker images to tag 20220908-060034-62bdc91b1 add d09d32e849 [CI] Update

[tvm] branch last-successful updated (4f4bc26607 -> ed630122c2)

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 4f4bc26607 [MetaSchedule] Mark two tests as xfail (#12733) add ed630122c2 [Test] Add

[tvm] branch last-successful updated (cd99ca64cb -> 4f4bc26607)

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 cd99ca64cb [Relay] Change when int8 operations are converted to int16 on Arm (#12671) add 2d36e46007

[tvm] 01/01: [CI] Update Docker images to tag 20220908-060034-62bdc91b1

[CI] Update Docker images to tag 20220908-060034-62bdc91b1 Updates all Docker images to tag 20220908-060034-62bdc91b1, to update TensorFlow/TFLite/Keras to 2.9, and cascaded dependencies such as numpy. Updates ethos-u-vela to 3.4.0. It also brings ONNX and PyTorch

[tvm] branch update_docker_tf291 created (now 1a94c9224f)

This is an automated email from the ASF dual-hosted git repository. leandron pushed a change to branch update_docker_tf291 in repository https://gitbox.apache.org/repos/asf/tvm.git at 1a94c9224f [CI] Update Docker images to tag 20220908-060034-62bdc91b1 This branch includes the following

[GitHub] [tvm] leandron opened a new pull request, #12738: [CI] Update Docker images to tag 20220908-060034-62bdc91b1

leandron opened a new pull request, #12738: URL: https://github.com/apache/tvm/pull/12738 Updates all Docker images to tag `20220908-060034-62bdc91b1`, to update TensorFlow/TFLite/Keras to 2.9, and cascaded dependencies such as numpy. Updates ethos-u-vela to 3.4.0. It also

[GitHub] [tvm] guberti commented on a diff in pull request #12495: [microTVM] add the option to open a saved micro project for debugging

guberti commented on code in PR #12495: URL: https://github.com/apache/tvm/pull/12495#discussion_r966087664 ## python/tvm/micro/session.py: ## @@ -275,25 +279,44 @@ def compile_and_create_micro_session( project_options: dict Options for the microTVM API Server

[tvm] branch main updated: [TIR] Handle axis_separators during FlattenBuffer (#12652)

This is an automated email from the ASF dual-hosted git repository. wrongtest 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 b2bd434ef9 [TIR] Handle axis_separators during

[GitHub] [tvm] wrongtest-intellif merged pull request #12652: [TIR] Handle axis_separators during FlattenBuffer

wrongtest-intellif merged PR #12652: URL: https://github.com/apache/tvm/pull/12652 -- 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 nightly-docker-update updated (d3e14dd1a8 -> 9a13fdde46)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch nightly-docker-update in repository https://gitbox.apache.org/repos/asf/tvm.git omit d3e14dd1a8 [ci][docker] Nightly Docker image update add abb2aa062f [TIR] Add

[GitHub] [tvm] lhutton1 commented on a diff in pull request #12731: [BugFix][UMA] Bugfix of target attr and fixed link in tutorial

lhutton1 commented on code in PR #12731: URL: https://github.com/apache/tvm/pull/12731#discussion_r966003184 ## python/tvm/relay/backend/contrib/uma/backend.py: ## @@ -278,7 +278,7 @@ def register(self) -> None: """ registration_func =

[GitHub] [tvm] Lunderberg commented on a diff in pull request #12720: [TIR] Implement API for padded layout transformations

Lunderberg commented on code in PR #12720: URL: https://github.com/apache/tvm/pull/12720#discussion_r965998079 ## src/tir/schedule/primitive/layout_transformation.cc: ## @@ -16,12 +16,580 @@ * specific language governing permissions and limitations * under the License. */

[GitHub] [tvm] Lunderberg commented on a diff in pull request #12720: [TIR] Implement API for padded layout transformations

Lunderberg commented on code in PR #12720: URL: https://github.com/apache/tvm/pull/12720#discussion_r965997578 ## src/tir/schedule/primitive/layout_transformation.cc: ## @@ -16,12 +16,580 @@ * specific language governing permissions and limitations * under the License. */

[GitHub] [tvm] Mousius merged pull request #12737: [Test] Add tvm.testing.requires_libtorch

Mousius merged PR #12737: URL: https://github.com/apache/tvm/pull/12737 -- 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: [Test] Add tvm.testing.requires_libtorch (#12737)

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 ed630122c2 [Test] Add tvm.testing.requires_libtorch

[GitHub] [tvm] Mousius merged pull request #12733: [MetaSchedule] Mark two tests as xfail

Mousius merged PR #12733: URL: https://github.com/apache/tvm/pull/12733 -- 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 (2d36e46007 -> 4f4bc26607)

This is an automated email from the ASF dual-hosted git repository. mousius pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 2d36e46007 [CI][AArch64] Mark tests to be skipped due to torch crash (#12730) add 4f4bc26607 [MetaSchedule] Mark

[tvm] branch main updated (cd99ca64cb -> 2d36e46007)

This is an automated email from the ASF dual-hosted git repository. mousius pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from cd99ca64cb [Relay] Change when int8 operations are converted to int16 on Arm (#12671) add 2d36e46007 [CI][AArch64]

[GitHub] [tvm] Mousius merged pull request #12730: [CI][AArch64] Mark tests to be skipped due to torch crash

Mousius merged PR #12730: URL: https://github.com/apache/tvm/pull/12730 -- 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] leandron commented on issue #12732: [Bug] Meta-scheduler tests failing in `test_meta_schedule_integration.py`

leandron commented on issue #12732: URL: https://github.com/apache/tvm/issues/12732#issuecomment-1240721659 Also cc @Hzfengsy as suggested by tvm-bot in the PR. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL

[GitHub] [tvm] valmat07 commented on a diff in pull request #12490: [OpenCL] Enable OpenCL for GPU tests

valmat07 commented on code in PR #12490: URL: https://github.com/apache/tvm/pull/12490#discussion_r965919608 ## tests/scripts/task_python_integration.sh: ## @@ -61,12 +61,16 @@ run_pytest cython ${TVM_INTEGRATION_TESTSUITE_NAME}-dso_plugin_module-1 apps/dso run_pytest ctypes

[GitHub] [tvm] zhiwei-dong commented on issue #11371: [Bug] Can't run prequantized tflite model through MicroTVM

zhiwei-dong commented on issue #11371: URL: https://github.com/apache/tvm/issues/11371#issuecomment-1240658866 no, but we can contact use email for more details, dongz...@outlook.con -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [tvm] Theoo1997 commented on issue #11371: [Bug] Can't run prequantized tflite model through MicroTVM

Theoo1997 commented on issue #11371: URL: https://github.com/apache/tvm/issues/11371#issuecomment-1240597647 Hi, I face the same problem. Do we have any update about the issue? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

[tvm] branch last-successful updated (62bdc91b1a -> cd99ca64cb)

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 62bdc91b1a Add Arm DSP implementation of Depthwise Conv2D (#12448) add cd99ca64cb [Relay] Change when

[GitHub] [tvm] leandron opened a new pull request, #12737: [Test] Add tvm.testing.requires_libtorch

leandron opened a new pull request, #12737: URL: https://github.com/apache/tvm/pull/12737 Create a specific test dependency to map to USE_LIBTORCH, which is disabled by deafult, and is independent from torch being installed on the underlying machine, so it causes problems in machines that

[GitHub] [tvm] leandron opened a new issue, #12736: [Bug] USE_LIBTORCH is disabled in all builds

leandron opened a new issue, #12736: URL: https://github.com/apache/tvm/issues/12736 On my journey in enabling Integration tests in AArch64, I stumbled upon `ctypes.tests.python.contrib.test_libtorch_ops.test_backend`, which crashes running integration tests on machines with torch

[GitHub] [tvm] luyaor opened a new issue, #12735: [Bug] TVM errors with an ONNX model (probably related to Resize Operation)

luyaor opened a new issue, #12735: URL: https://github.com/apache/tvm/issues/12735 When compiling [following ONNX model](https://github.com/apache/tvm/files/9526032/bug-no2.zip) with TVM, the compiler fails with errors. I think it is probably related to the Resize operation.

[GitHub] [tvm] luyaor opened a new issue, #12734: [Bug] an ONNX model after compiling with TVM is inconsistent with ONNXRuntime

luyaor opened a new issue, #12734: URL: https://github.com/apache/tvm/issues/12734 ### Expected behavior When feed the same input into the same model, one in TVM, another in ONNXRuntime, we supposed that their results are the same.

[GitHub] [tvm] github-actions[bot] commented on pull request #12454: [Target] Add Target Parser for Arm(R) Cortex(R) A-Profile CPUs

github-actions[bot] commented on PR #12454: URL: https://github.com/apache/tvm/pull/12454#issuecomment-1240485424 It has been a while since this PR was updated, @u99127 please leave a review or address the outstanding comments. @Mousius if this PR is still a work in progress, please

[GitHub] [tvm] leandron opened a new pull request, #12733: [MetaSchedule] Mark two tests as xfail

leandron opened a new pull request, #12733: URL: https://github.com/apache/tvm/pull/12733 This patch marks two tests as xfail for further investigation: * `test_meta_schedule_integration_extract_from_resnet_with_filter_func` * `test_meta_schedule_integration_extract_from_resnet`

[GitHub] [tvm] valmat07 commented on pull request #12490: [OpenCL] Enable OpenCL for GPU tests

valmat07 commented on PR #12490: URL: https://github.com/apache/tvm/pull/12490#issuecomment-1240461906 @tvm-bot rerun -- 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] leandron opened a new issue, #12732: [Bug] Meta-scheduler tests failing in `test_meta_schedule_integration.py`

leandron opened a new issue, #12732: URL: https://github.com/apache/tvm/issues/12732 There are 2 meta-scheduler tests failing when we run these tests in CI on machines that have torch installed. The last change I could track that touches on that part is in the context of #12520 - I didn't

[GitHub] [tvm] MichaelJKlaiber commented on pull request #12731: [BugFix][UMA] Bugfix of target attr and fixed link in tutorial

MichaelJKlaiber commented on PR #12731: URL: https://github.com/apache/tvm/pull/12731#issuecomment-1240437628 @cgerum @areusch -- 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] MichaelJKlaiber opened a new pull request, #12731: [BugFix][UMA] Bugfix of target attr and fixed link in tutorial

MichaelJKlaiber opened a new pull request, #12731: URL: https://github.com/apache/tvm/pull/12731 There was a flaw in UMA backend.py that triggered an error when for passing target attributes. It is fixed. A link in the UMA tutorial was broken and fixed by this PR. -- This is an

[GitHub] [tvm] sfvaroglu commented on pull request #12729: Upgrade onnx, onnxruntime, onnxoptimizer

sfvaroglu commented on PR #12729: URL: https://github.com/apache/tvm/pull/12729#issuecomment-1240427622 > Thanks for the PR. Just a quick note that modifications in these scripts are not currently _tested_ in CI, as the current CI workflow won't pickup the images created by a given PR to

[GitHub] [tvm] Mousius merged pull request #12671: [Relay] Change when int8 operations are converted to int16 on Arm

Mousius merged PR #12671: URL: https://github.com/apache/tvm/pull/12671 -- 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 (62bdc91b1a -> cd99ca64cb)

This is an automated email from the ASF dual-hosted git repository. mousius pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 62bdc91b1a Add Arm DSP implementation of Depthwise Conv2D (#12448) add cd99ca64cb [Relay] Change when int8

[GitHub] [tvm] leandron opened a new pull request, #12730: [CI][AArch64] Mark tests to be skipped due to torch crash

leandron opened a new pull request, #12730: URL: https://github.com/apache/tvm/pull/12730 Some integration tests are not being run on CI due to the configuration of the machine with onnx and torch not calling the integration tests script. This patch skips two more tests failing with

  1   2   >