[GitHub] [tvm] Qianshui-Jiang commented on pull request #15685: [Target][TOPI] Use LLVM for x86 CPU feature lookup

Qianshui-Jiang commented on PR #15685: URL: https://github.com/apache/tvm/pull/15685#issuecomment-1717046584 @cbalint13 @vvchernov big thanks for your hard work and dicussion! Here is few comments. Actually before the CasecadeLake we use avx512 to handle the 8bit and 16bit integer, so

[GitHub] [tvm] jikechao closed issue #14868: [Bug][Relay] crash at shape checking in SimpleRNN at Keras frontend

jikechao closed issue #14868: [Bug][Relay] crash at shape checking in SimpleRNN at Keras frontend URL: https://github.com/apache/tvm/issues/14868 -- 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 nightly updated (4d7e93cd7c -> 7fd4704003)

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 4d7e93cd7c [TIR] Output DeclBuffer in LowerThreadAllreduce (#15646) add d8136fbaa1 [Relay][Bugfix] Fix the wron

[tvm] branch main updated: fix _convert_simple_rnn (#15723)

This is an automated email from the ASF dual-hosted git repository. echuraev 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 7fd4704003 fix _convert_simple_rnn (#15723) 7fd470400

[GitHub] [tvm] echuraev merged pull request #15723: fix _convert_simple_rnn

echuraev merged PR #15723: URL: https://github.com/apache/tvm/pull/15723 -- 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.

[GitHub] [tvm] Thrsu commented on pull request #15734: [Unity] [Bugfix] Fix KeyError: 'padding' in _avg_pool2d implementation

Thrsu commented on PR #15734: URL: https://github.com/apache/tvm/pull/15734#issuecomment-1716893455 > Would be great if you could add a regression test. > > BTW, tvm bot does not work on unity branch :( Sure, I have added a regression test as requested. Please recheck. -- Thi

[GitHub] [tvm] Thrsu commented on pull request #15734: [Unity] [Bugfix] Fix KeyError: 'padding' in _avg_pool2d implementation

Thrsu commented on PR #15734: URL: https://github.com/apache/tvm/pull/15734#issuecomment-1716891491 > @Thrsu Thanks for the PR. > Please change the title to `[Unity][Bugfix]Fix KeyError: 'padding' in _avg_pool2d implementation` and add a test case. Thank you for your review, I have cha

[GitHub] [tvm] junrushao opened a new pull request, #15737: [Relax][VM] Add additional flags for picojson

junrushao opened a new pull request, #15737: URL: https://github.com/apache/tvm/pull/15737 This commits adds `__STDC_FORMAT_MACROS` when including picojson in C++. This should fix a recent build issue as below: ``` In file included from src/runtime/relax_vm/ndarray_cache_support.cc

[GitHub] [tvm] leiwen83 closed pull request #15576: don't do actual profile when input is dynamic shape

leiwen83 closed pull request #15576: don't do actual profile when input is dynamic shape URL: https://github.com/apache/tvm/pull/15576 -- 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 co

[GitHub] [tvm] Hzfengsy commented on pull request #15734: Fix KeyError: 'padding' in _avg_pool2d implementation

Hzfengsy commented on PR #15734: URL: https://github.com/apache/tvm/pull/15734#issuecomment-1716796870 Would be great if you could add a regression test. BTW, tvm bot does not work on unity branch :( -- This is an automated message from the Apache Git Service. To respond to the mess

[GitHub] [tvm] github-actions[bot] commented on pull request #15734: Fix KeyError: 'padding' in _avg_pool2d implementation

github-actions[bot] commented on PR #15734: URL: https://github.com/apache/tvm/pull/15734#issuecomment-1716795193 Failed to re-run CI in https://github.com/apache/tvm/actions/runs/6166768657 ``` Traceback (most recent call last): File "ci/scripts/github/github_tvmbot.py

[GitHub] [tvm] jikechao commented on pull request #15734: Fix KeyError: 'padding' in _avg_pool2d implementation

jikechao commented on PR #15734: URL: https://github.com/apache/tvm/pull/15734#issuecomment-1716795027 @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 uns

[GitHub] [tvm] vinx13 opened a new pull request, #15736: [Unity] Skip shape checking on transformed params

vinx13 opened a new pull request, #15736: URL: https://github.com/apache/tvm/pull/15736 cc @masahi @sunggg -- 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] csullivan commented on a diff in pull request #15672: [IR] Implemented Variant<...> container

csullivan commented on code in PR #15672: URL: https://github.com/apache/tvm/pull/15672#discussion_r1323692148 ## tests/cpp/container_test.cc: ## @@ -853,3 +854,23 @@ TEST(Optional, PackedCall) { test_ffi(s, static_cast(kTVMObjectHandle)); test_ffi(String(s), static_cast(k

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323596774 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323595717 ## python/tvm/target/target.py: ## @@ -148,6 +150,45 @@ def export(self): def with_host(self, host=None): return _ffi_api.WithHost(self, Target(host)) +

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323595003 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323593544 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323590402 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323589599 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323589278 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323589023 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323587239 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323586916 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323582365 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[GitHub] [tvm] junrushao commented on a diff in pull request #15714: [Target][Device] Auto detect target and create device from str in torch style

junrushao commented on code in PR #15714: URL: https://github.com/apache/tvm/pull/15714#discussion_r1323581208 ## python/tvm/target/detect_target.py: ## @@ -0,0 +1,169 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. Se

[tvm] branch main updated: Revert "[CodeGenC] Handle GlobalVar callee as internal function call" (#15725)

This is an automated email from the ASF dual-hosted git repository. ruihangl 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 e88d0d4be1 Revert "[CodeGenC] Handle GlobalVar callee

[GitHub] [tvm] MasterJH5574 merged pull request #15725: Revert "[CodeGenC] Handle GlobalVar callee as internal function call"

MasterJH5574 merged PR #15725: URL: https://github.com/apache/tvm/pull/15725 -- 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.apa

[GitHub] [tvm] junrushao merged pull request #15670: [Unity][Frontend][NN] Enable tuple/list input

junrushao merged PR #15670: URL: https://github.com/apache/tvm/pull/15670 -- 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 unity updated: [Unity][Frontend][NN] Enable tuple/list input (#15670)

This is an automated email from the ASF dual-hosted git repository. junrushao 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 cdf40be5ca [Unity][Frontend][NN] Enable tuple/list

[GitHub] [tvm] jinhongyii commented on pull request #15735: [Unity][disco] Change collective communication to destination-passing style

jinhongyii commented on PR #15735: URL: https://github.com/apache/tvm/pull/15735#issuecomment-1716402520 cc: @junrushao @tqchen -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comm

[GitHub] [tvm] jinhongyii opened a new pull request, #15735: [Unity][disco] Change collective communication to destination-passing style

jinhongyii opened a new pull request, #15735: URL: https://github.com/apache/tvm/pull/15735 (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] echuraev commented on pull request #15723: fix _convert_simple_rnn

echuraev commented on PR #15723: URL: https://github.com/apache/tvm/pull/15723#issuecomment-1716339670 @haoyang9804, I have restarted CI. In case of further errors, please try to rebase your branch to the latest mainline. -- This is an automated message from the Apache Git Service. To res

[GitHub] [tvm] echuraev commented on pull request #15723: fix _convert_simple_rnn

echuraev commented on PR #15723: URL: https://github.com/apache/tvm/pull/15723#issuecomment-1716338282 @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 uns

[GitHub] [tvm] vvchernov commented on pull request #15723: fix _convert_simple_rnn

vvchernov commented on PR #15723: URL: https://github.com/apache/tvm/pull/15723#issuecomment-1716266284 I've rechecked PRs: #15714 and #15709 have the same issue, but the next PRs do not have. Possibly it is the best way to restart this CI -- This is an automated message from the Apache G

[GitHub] [tvm] vvchernov commented on pull request #15723: fix _convert_simple_rnn

vvchernov commented on PR #15723: URL: https://github.com/apache/tvm/pull/15723#issuecomment-1716250601 Hello @echuraev! Looks like it isproblem from jenkins: ```[2023-09-12T17:54:08.315Z] + ./ci/scripts/jenkins/s3.py --action upload --bucket tvm-jenkins-artifacts-prod --prefix tvm/PR-15

[GitHub] [tvm] masahi commented on pull request #15708: [Relay] Simplify Conv->bias_add->mul->add to Conv->bias_add

masahi commented on PR #15708: URL: https://github.com/apache/tvm/pull/15708#issuecomment-1716237070 Have you tried `FoldScaleAxis`? Combined with `SimplifyExpr` I think it already does such optimization. -- This is an automated message from the Apache Git Service. To respond to the mess

[GitHub] [tvm] masahi commented on a diff in pull request #15679: [Unity] Support Padding Reversal in Alter-Op pass

masahi commented on code in PR #15679: URL: https://github.com/apache/tvm/pull/15679#discussion_r1323414157 ## python/tvm/relax/transform/legalize_ops/manipulate.py: ## @@ -205,3 +213,16 @@ def te_layout_transform(data, name): output_dtype = call_args[0].struct_info.dtype

[GitHub] [tvm] Lunderberg commented on a diff in pull request #15672: [IR] Implemented Variant<...> container

Lunderberg commented on code in PR #15672: URL: https://github.com/apache/tvm/pull/15672#discussion_r1323342788 ## tests/cpp/container_test.cc: ## @@ -853,3 +854,23 @@ TEST(Optional, PackedCall) { test_ffi(s, static_cast(kTVMObjectHandle)); test_ffi(String(s), static_cast(

[GitHub] [tvm] Lunderberg commented on a diff in pull request #15694: [Unity] Implemented SameShapeConstraint for dataflow pattern matches

Lunderberg commented on code in PR #15694: URL: https://github.com/apache/tvm/pull/15694#discussion_r1323329466 ## src/relax/ir/dataflow_matcher.cc: ## @@ -443,6 +444,92 @@ bool DFPatternMatcher::VisitDFPattern_(const ShapePatternNode* op, const Expr& e return false; } +O

[GitHub] [tvm] p3achyjr opened a new pull request, #15733: [TFLite][Frontend] Support quantized floor_mod

p3achyjr opened a new pull request, #15733: URL: https://github.com/apache/tvm/pull/15733 As part of https://github.com/apache/tvm/issues/15148, this PR adds support for floor_div. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to Git

[tvm] 01/01: Revert "[CodeGenC] Handle GlobalVar callee as internal function call (#15103)"

This is an automated email from the ASF dual-hosted git repository. junrushao pushed a commit to branch revert-15103-codegen_c_support_subroutine_calls in repository https://gitbox.apache.org/repos/asf/tvm.git commit 45eb402bd49e152c46ab8e31bdd54626a7a5d6b0 Author: Junru Shao AuthorDate: Mon Se

[tvm] branch revert-15103-codegen_c_support_subroutine_calls updated (cf1766cbbb -> 45eb402bd4)

This is an automated email from the ASF dual-hosted git repository. junrushao pushed a change to branch revert-15103-codegen_c_support_subroutine_calls in repository https://gitbox.apache.org/repos/asf/tvm.git omit cf1766cbbb Revert "[CodeGenC] Handle GlobalVar callee as internal function

[GitHub] [tvm-rfcs] tqchen commented on pull request #89: [RFC] Relax Upstreaming

tqchen commented on PR #89: URL: https://github.com/apache/tvm-rfcs/pull/89#issuecomment-1715756599 sending another reminder for everyone to chime into related unity discussion threads https://discuss.tvm.apache.org/c/development/unity/14, love to see your participations on all the technica

[GitHub] [tvm] twzhyyxwhez31057 opened a new issue, #15732: [Bug] [Meta-Schedule]can not auto-tuning for android-Adreno by rpc

twzhyyxwhez31057 opened a new issue, #15732: URL: https://github.com/apache/tvm/issues/15732 Hi, I tried to auto-tuning a IRModule using meta-schedule, however I met this error: "TVMError: Unsupported target: opencl -keys=opencl,gpu -max_function_args=128 -max_num_threads=256 -max_share

[GitHub] [tvm] vvchernov commented on pull request #15723: fix _convert_simple_rnn

vvchernov commented on PR #15723: URL: https://github.com/apache/tvm/pull/15723#issuecomment-1715647907 cc @echuraev -- 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 uns

[GitHub] [tvm] tlopex commented on issue #15148: [Tracking Issue] TFLite operator support

tlopex commented on issue #15148: URL: https://github.com/apache/tvm/issues/15148#issuecomment-1715620857 @p3achyjr Thanks. You set me a really great example. I'll try it again. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

[tvm] branch main updated: [TFLite][Frontend] Support quantized floor_div (#15724)

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 e3055c1970 [TFLite][Frontend] Support quantized floor_d

[GitHub] [tvm] lhutton1 commented on pull request #15724: [TFLite][Frontend] Support quantized floor_div

lhutton1 commented on PR #15724: URL: https://github.com/apache/tvm/pull/15724#issuecomment-1715492950 Thanks @p3achyjr @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 com

[GitHub] [tvm] lhutton1 merged pull request #15724: [TFLite][Frontend] Support quantized floor_div

lhutton1 merged PR #15724: URL: https://github.com/apache/tvm/pull/15724 -- 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.

[GitHub] [tvm] rutkoor commented on pull request #15679: [Unity] Support Padding Reversal in Alter-Op pass

rutkoor commented on PR #15679: URL: https://github.com/apache/tvm/pull/15679#issuecomment-1715399793 Gentle reminder to please review this 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 above to go to the

[tvm] branch unity updated: [UNITY][Pass] Optimize redundant layout transform ops (#15678)

This is an automated email from the ASF dual-hosted git repository. masahi 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 0e800cf3f8 [UNITY][Pass] Optimize redundant layout tr

[GitHub] [tvm] masahi commented on a diff in pull request #15678: [UNITY][Pass] Optimize redundant layout transform ops

masahi commented on code in PR #15678: URL: https://github.com/apache/tvm/pull/15678#discussion_r1322614653 ## python/tvm/relax/transform/optimize_layout_transform.py: ## @@ -0,0 +1,75 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor licens

[GitHub] [tvm] ysh329 commented on issue #15716: [Bug] StringImm Object Can't Be Pass to C++ Side from Python Side

ysh329 commented on issue #15716: URL: https://github.com/apache/tvm/issues/15716#issuecomment-1715148854 > @junrushao Sorry for the late reply, I haven't try it, but I think it won't help, because our internal TVM repo haven't sync this commit yet, and the problem still will happen with a

[GitHub] [tvm] Thrsu opened a new issue, #15729: [Bug][Unity] TVMError when using relax to load model with Trilu operator

Thrsu opened a new issue, #15729: URL: https://github.com/apache/tvm/issues/15729 The error message suggests that there is an issue with converting the second argument for the trill operation. The error message is as follows: `TVMError: In function relax.op.tril(0: RelayExpr, 1: int) -> Rel