[GitHub] [tvm] Lantianyou opened a new pull request, #15527: feat: fix type files

Lantianyou opened a new pull request, #15527: URL: https://github.com/apache/tvm/pull/15527 (no comment) -- 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-m

[GitHub] [tvm] tvm-bot commented on pull request #15527: feat: fix type files

tvm-bot commented on PR #15527: URL: https://github.com/apache/tvm/pull/15527#issuecomment-1674297665 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] Lantianyou opened a new pull request, #15528: Feature/cache with indexdb

Lantianyou opened a new pull request, #15528: URL: https://github.com/apache/tvm/pull/15528 (no comment) -- 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-m

[GitHub] [tvm] tvm-bot commented on pull request #15528: Feature/cache with indexdb

tvm-bot commented on PR #15528: URL: https://github.com/apache/tvm/pull/15528#issuecomment-1674298637 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] Lantianyou closed pull request #15527: feat: fix type files

Lantianyou closed pull request #15527: feat: fix type files URL: https://github.com/apache/tvm/pull/15527 -- 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] Lantianyou closed pull request #15528: Feature/cache with indexdb

Lantianyou closed pull request #15528: Feature/cache with indexdb URL: https://github.com/apache/tvm/pull/15528 -- 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] tvm-bot commented on pull request #15529: [quantize] fix bug of annotate for output of add op

tvm-bot commented on PR #15529: URL: https://github.com/apache/tvm/pull/15529#issuecomment-1674360904 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] MingkangW opened a new pull request, #15529: [quantize] fix bug of annotate for output of add op

MingkangW opened a new pull request, #15529: URL: https://github.com/apache/tvm/pull/15529 The type of add op`s output is activation, it should annotate by QAnnotateKind.ACTIVATION. If not, the graph will cast int32 into int8 directly without quantized, when quantize resnet. It will product

[tvm] branch main updated: Remove duplicate the word (#15524)

This is an automated email from the ASF dual-hosted git repository. ekalda 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 ed8b82c5d6 Remove duplicate the word (#15524) ed8b82c5d

[GitHub] [tvm] ekalda commented on pull request #15524: Remove duplicate the word

ekalda commented on PR #15524: URL: https://github.com/apache/tvm/pull/15524#issuecomment-1674365340 Thanks for this improvement @BaseMax and welcome to the TVM community! -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and us

[GitHub] [tvm] ekalda merged pull request #15524: Remove duplicate the word

ekalda merged PR #15524: URL: https://github.com/apache/tvm/pull/15524 -- 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

[GitHub] [tvm] lhutton1 commented on a diff in pull request #15519: [TEST] Run tests/python/relay/aot tests in ci-cortexm

lhutton1 commented on code in PR #15519: URL: https://github.com/apache/tvm/pull/15519#discussion_r1291033568 ## tests/scripts/task_python_integration.sh: ## @@ -64,7 +64,7 @@ run_pytest ctypes ${TVM_INTEGRATION_TESTSUITE_NAME}-integration tests/python/int run_pytest ctypes ${

[GitHub] [tvm] ekalda commented on a diff in pull request #15519: [TEST] Run tests/python/relay/aot tests in ci-cortexm

ekalda commented on code in PR #15519: URL: https://github.com/apache/tvm/pull/15519#discussion_r1291062842 ## tests/scripts/task_python_integration.sh: ## @@ -64,7 +64,7 @@ run_pytest ctypes ${TVM_INTEGRATION_TESTSUITE_NAME}-integration tests/python/int run_pytest ctypes ${TV

[GitHub] [tvm] lhutton1 commented on a diff in pull request #15519: [TEST] Run tests/python/relay/aot tests in ci-cortexm

lhutton1 commented on code in PR #15519: URL: https://github.com/apache/tvm/pull/15519#discussion_r1291065085 ## tests/scripts/task_python_integration.sh: ## @@ -64,7 +64,7 @@ run_pytest ctypes ${TVM_INTEGRATION_TESTSUITE_NAME}-integration tests/python/int run_pytest ctypes ${

[GitHub] [tvm] lhutton1 merged pull request #15519: [TEST] Run tests/python/relay/aot tests in ci-cortexm

lhutton1 merged PR #15519: URL: https://github.com/apache/tvm/pull/15519 -- 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.

[tvm] branch main updated (ed8b82c5d6 -> 624f8a73c7)

This is an automated email from the ASF dual-hosted git repository. lukhut pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from ed8b82c5d6 Remove duplicate the word (#15524) add 624f8a73c7 [TEST] Run tests/python/relay/aot tests in ci-cortexm (#

[GitHub] [tvm] lhutton1 commented on pull request #15519: [TEST] Run tests/python/relay/aot tests in ci-cortexm

lhutton1 commented on PR #15519: URL: https://github.com/apache/tvm/pull/15519#issuecomment-1674398261 Thanks @ekalda! -- 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

[GitHub] [tvm] BaseMax opened a new pull request, #15530: Remove duplicate msg word and condition inside the function doc

BaseMax opened a new pull request, #15530: URL: https://github.com/apache/tvm/pull/15530 Hi Apache Team, I'm thrilled to submit my third contribution to Apache! I've addressed the issue of duplicate word inside function comment in the code. Paying attention to such details is vital f

[GitHub] [tvm] tvm-bot commented on pull request #15530: Remove duplicate msg word and condition inside the function doc

tvm-bot commented on PR #15530: URL: https://github.com/apache/tvm/pull/15530#issuecomment-1674449420 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] cbalint13 commented on issue #15522: [Bug] [MetaScheduler] [TensorIR] Stride values are not inferred within _impl() block.

cbalint13 commented on issue #15522: URL: https://github.com/apache/tvm/issues/15522#issuecomment-1674470830 I've tracked down the issue. 1. LLVM lowered code, before [this->Optimize()](https://github.com/apache/tvm/blob/ed8b82c5d6ea91e70d374988b16b47f64cd83f63/src/target/llvm/codegen

[GitHub] [tvm] tvm-bot commented on pull request #15531: [Unity][DLight] Update GEMV Rule for Mali GPUs

tvm-bot commented on PR #15531: URL: https://github.com/apache/tvm/pull/15531#issuecomment-1674502582 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] cbalint13 opened a new pull request, #15532: [MetaSchedule] Enable subprocess to stdout for DEBUG level

cbalint13 opened a new pull request, #15532: URL: https://github.com/apache/tvm/pull/15532 Hi folks, Small enhancement for catching error messages from local runners. The need raise from: #15522 as a ease to spot, pin & debug things. Thanks, ~Cristian. -- This

[GitHub] [tvm] tvm-bot commented on pull request #15532: [MetaSchedule] Enable subprocess to stdout for DEBUG level

tvm-bot commented on PR #15532: URL: https://github.com/apache/tvm/pull/15532#issuecomment-1674508172 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm-rfcs] mbaret commented on pull request #102: [Process RFC] Clarify Community Strategy Decision Process

mbaret commented on PR #102: URL: https://github.com/apache/tvm-rfcs/pull/102#issuecomment-1674529045 +1 I think this is a substantially improved proposal compared with the similar RFC from last year, being more concise and using a 2/3rds majority which feels appropriate. -- This is a

[GitHub] [tvm] tqchen merged pull request #15531: [Unity][DLight] Update GEMV Rule for Mali GPUs

tqchen merged PR #15531: URL: https://github.com/apache/tvm/pull/15531 -- 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

[tvm] branch unity updated: [Unity][DLight] Update GEMV Rule for Mali GPUs (#15531)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch unity in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/unity by this push: new a012fe0df4 [Unity][DLight] Update GEMV Rule for Mali

[GitHub] [tvm] lhutton1 merged pull request #15525: Fix typo mistake and change whethe to whether

lhutton1 merged PR #15525: URL: https://github.com/apache/tvm/pull/15525 -- 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.

[tvm] branch main updated: Fix typo mistake and change whethe to whether (#15525)

This is an automated email from the ASF dual-hosted git repository. lukhut 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 326f8e7435 Fix typo mistake and change whethe to whethe

[GitHub] [tvm] lhutton1 commented on pull request #15525: Fix typo mistake and change whethe to whether

lhutton1 commented on PR #15525: URL: https://github.com/apache/tvm/pull/15525#issuecomment-1674855451 Thanks @BaseMax @Hzfengsy! -- 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 comm

[GitHub] [tvm] ekalda commented on pull request #15472: [Relay][TFLite] Fix in qnn.conv2d when parameter groups not equal to 1

ekalda commented on PR #15472: URL: https://github.com/apache/tvm/pull/15472#issuecomment-1674902879 Thanks for the explanation, makes sense to me :) What I was asking was to amend the *commit message body* as I don't think "There was a bug" is particularly informative in the commit history

[GitHub] [tvm] yongwww commented on a diff in pull request #15500: [Unity][MSC][M0.1] Enable set name and layout for exprs

yongwww commented on code in PR #15500: URL: https://github.com/apache/tvm/pull/15500#discussion_r1291577224 ## ci/jenkins/unity_jenkinsfile.groovy: ## @@ -318,6 +318,7 @@ stage('Build and Test') { sh "${docker_run} ${ci_gpu} ./tests/scripts/task_config_build_gpu.sh

[GitHub] [tvm] cbalint13 closed issue #15522: [Bug] [MetaScheduler] [TensorIR] Stride values are not inferred within _impl() block.

cbalint13 closed issue #15522: [Bug] [MetaScheduler] [TensorIR] Stride values are not inferred within _impl() block. URL: https://github.com/apache/tvm/issues/15522 -- 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] tqchen merged pull request #15447: [Unity] Multi-device support for Relax

tqchen merged PR #15447: URL: https://github.com/apache/tvm/pull/15447 -- 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

[tvm] branch unity updated: [Unity] Multi-device support for Relax (#15447)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch unity in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/unity by this push: new 2226a1f558 [Unity] Multi-device support for Relax (#1

[GitHub] [tvm] tqchen commented on pull request #15447: [Unity] Multi-device support for Relax

tqchen commented on PR #15447: URL: https://github.com/apache/tvm/pull/15447#issuecomment-1675267593 Thank you @yongwww ! this is 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 specif

[GitHub] [tvm] yongwww commented on pull request #15511: Remove IRModule Dependency from Target

yongwww commented on PR #15511: URL: https://github.com/apache/tvm/pull/15511#issuecomment-1675282541 cc: @tqchen @junrushao -- 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.

[GitHub] [tvm] echuraev opened a new pull request, #15533: [Relay] Disable exception for ADT in mixed precision pass

echuraev opened a new pull request, #15533: URL: https://github.com/apache/tvm/pull/15533 If topology contains while loop and we want to transform it to mixed precision then we get an exception that "ADT are not supported for mixed precision pass". It happens, because while loop implemented

[GitHub] [tvm] tvm-bot commented on pull request #15533: [Relay] Disable exception for ADT in mixed precision pass

tvm-bot commented on PR #15533: URL: https://github.com/apache/tvm/pull/15533#issuecomment-1675380393 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] slyubomirsky commented on pull request #15455: [Unity] Implement R.macro for Relax macros

slyubomirsky commented on PR #15455: URL: https://github.com/apache/tvm/pull/15455#issuecomment-1675390718 I'll review, sorry I didn't see the pings. -- 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] tqchen merged pull request #15511: Remove IRModule Dependency from Target

tqchen merged PR #15511: URL: https://github.com/apache/tvm/pull/15511 -- 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

[tvm] branch main updated (326f8e7435 -> 81fd9f3476)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 326f8e7435 Fix typo mistake and change whethe to whether (#15525) add 81fd9f3476 Remove IRModule Dependency from Targe

[GitHub] [tvm] slyubomirsky commented on pull request #15455: [Unity] Implement R.macro for Relax macros

slyubomirsky commented on PR #15455: URL: https://github.com/apache/tvm/pull/15455#issuecomment-1675424031 Can macros take in Relax vars as arguments and define new Relax vars? That would be an important test case for hygienic macros. Otherwise, everything in this PR looks good to me. --

[GitHub] [tvm] sunggg opened a new pull request, #15534: [Unity][BYOC] Make `MergeCompositeFunctions` append codegen name at the end of function name

sunggg opened a new pull request, #15534: URL: https://github.com/apache/tvm/pull/15534 This PR is followup of PR https://github.com/apache/tvm/pull/15491. By appending the codegen name at the end of function name, this PR make `MergeCompositeFunctions` explicitly show which functions

[GitHub] [tvm] tvm-bot commented on pull request #15534: [Unity][BYOC] Make `MergeCompositeFunctions` append codegen name at the end of function name

tvm-bot commented on PR #15534: URL: https://github.com/apache/tvm/pull/15534#issuecomment-1675475528 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] thaisacs opened a new pull request, #15535: fixed search task comment

thaisacs opened a new pull request, #15535: URL: https://github.com/apache/tvm/pull/15535 (no comment) -- 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-mai

[GitHub] [tvm] tvm-bot commented on pull request #15535: fixed search task comment

tvm-bot commented on PR #15535: URL: https://github.com/apache/tvm/pull/15535#issuecomment-1675594807 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] MingkangW commented on pull request #15529: [quantize] fix bug of annotate for output of add op

MingkangW commented on PR #15529: URL: https://github.com/apache/tvm/pull/15529#issuecomment-1675602767 @cbalint13 I have added test cases. If the annotation for add is not modified to ACTIVATION, the test case will not pass. -- This is an automated message from the Apache Git Service

[tvm] branch main updated: [MetaSchedule] Enable subprocess to stdout for DEBUG level (#15532)

This is an automated email from the ASF dual-hosted git repository. syfeng 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 6c33787cd2 [MetaSchedule] Enable subprocess to stdout f

[GitHub] [tvm] Hzfengsy merged pull request #15532: [MetaSchedule] Enable subprocess to stdout for DEBUG level

Hzfengsy merged PR #15532: URL: https://github.com/apache/tvm/pull/15532 -- 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.

[tvm] branch nightly updated (907b29e544 -> 6c33787cd2)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch nightly in repository https://gitbox.apache.org/repos/asf/tvm.git from 907b29e544 [TOPI] check empty array of x86 injective's iters (#15513) add ed8b82c5d6 Remove duplicate the word

[GitHub] [tvm] Jobhdez opened a new pull request, #15536: fix typo

Jobhdez opened a new pull request, #15536: URL: https://github.com/apache/tvm/pull/15536 (no comment) -- 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] tvm-bot commented on pull request #15536: fix typo

tvm-bot commented on PR #15536: URL: https://github.com/apache/tvm/pull/15536#issuecomment-1675719381 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from

[GitHub] [tvm] Archermmt commented on a diff in pull request #15500: [Unity][MSC][M0.1] Enable set name and layout for exprs

Archermmt commented on code in PR #15500: URL: https://github.com/apache/tvm/pull/15500#discussion_r1292119542 ## ci/jenkins/unity_jenkinsfile.groovy: ## @@ -318,6 +318,7 @@ stage('Build and Test') { sh "${docker_run} ${ci_gpu} ./tests/scripts/task_config_build_gpu.