[GitHub] [tvm] lixiaoquan commented on pull request #6890: [Relay] Fix a bug in tensor_array_scatter

lixiaoquan commented on pull request #6890: URL: https://github.com/apache/tvm/pull/6890#issuecomment-804625923 @kevinthesun Could you please take a look again? Thanks -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use

[GitHub] [tvm] xiebaiyuan opened a new issue #7725: do we have any check point to contine unfinished jobs?

xiebaiyuan opened a new issue #7725: URL: https://github.com/apache/tvm/issues/7725 do we have any check point to contine unfinished jobs? sometimes i have to stop my jobs , but i did not find a way to contine my job, i have to restart from 0 thanks -- This

[GitHub] [tvm] xiebaiyuan commented on issue #7705: build tvm failed with libbacktrace.a : ld: symbol(s) not found for architecture x86_64

xiebaiyuan commented on issue #7705: URL: https://github.com/apache/tvm/issues/7705#issuecomment-804549251 @tkonolige @tqchen ↑ is the message, and my config.cmake -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use

[GitHub] [tvm] xiebaiyuan commented on issue #7705: build tvm failed with libbacktrace.a : ld: symbol(s) not found for architecture x86_64

xiebaiyuan commented on issue #7705: URL: https://github.com/apache/tvm/issues/7705#issuecomment-804548672 return to this commit: c976a07fa -- 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

[GitHub] [tvm] xiebaiyuan commented on issue #7705: build tvm failed with libbacktrace.a : ld: symbol(s) not found for architecture x86_64

xiebaiyuan commented on issue #7705: URL: https://github.com/apache/tvm/issues/7705#issuecomment-804548198 config.cmake: ➜ build git:(c976a07fa) ✗ cat config.cmake # Licensed to the Apache Software Foundation (ASF) under one # or more contributor license agreements. See

[GitHub] [tvm] xiebaiyuan commented on issue #7705: build tvm failed with libbacktrace.a : ld: symbol(s) not found for architecture x86_64

xiebaiyuan commented on issue #7705: URL: https://github.com/apache/tvm/issues/7705#issuecomment-804547874 ➜ build git:(c976a07fa) ✗ make -j16 ===> Scanning dependencies of target project_libbacktrace Scanning dependencies of target tvm_objs [

[GitHub] [tvm] xiebaiyuan commented on issue #7705: build tvm failed with libbacktrace.a : ld: symbol(s) not found for architecture x86_64

xiebaiyuan commented on issue #7705: URL: https://github.com/apache/tvm/issues/7705#issuecomment-804547617 cmake .. => -- The C compiler identification is AppleClang 12.0.0.1232 -- The CXX compiler identification is AppleClang 12.0.0.1232 -- Detecting

[GitHub] [tvm] zhuwenxi commented on issue #7596: [BUG][CodeGenC]“tvm_call_packed” crashes when build with target “c”

zhuwenxi commented on issue #7596: URL: https://github.com/apache/tvm/issues/7596#issuecomment-804538954 @leeexyz , could you please check my screenshot posted above? This is definitely an issue that a variable named "tvm.contrib.cblas.matmul_packed" generated in the c source file, which

[GitHub] [tvm] tqchen commented on issue #7724: Minor bug in storage_access.cc

tqchen commented on issue #7724: URL: https://github.com/apache/tvm/issues/7724#issuecomment-804511979 thanks @pratikfegade, great catch can you craft a regression test case and send a patch ? -- This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [tvm] pratikfegade opened a new issue #7724: Minor bug in storage_access.cc

pratikfegade opened a new issue #7724: URL: https://github.com/apache/tvm/issues/7724 Hi, I have been playing around with TVM and it seems that the barrier insertion pass (implemented in `src/tir/storage_access.cc` and `src/tir/thread_storage_sync.cc`) does not handle the else case

[GitHub] [tvm] mehrdadh commented on pull request #7723: [microTVM] Update nrfjprog on reference virtual machine

mehrdadh commented on pull request #7723: URL: https://github.com/apache/tvm/pull/7723#issuecomment-804498464 @areusch please take a look when you get a chance. Thanks! -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use

[GitHub] [tvm] mehrdadh opened a new pull request #7723: [microTVM] Update nrfjprog on reference virtual machine

mehrdadh opened a new pull request #7723: URL: https://github.com/apache/tvm/pull/7723 This PR makes following changes: - It updates nrfjprog on reference machine to version 10.12.1 which fixes programming on nrf5340dk board. - Adds test for nrf5340dk board to RVM integration

[GitHub] [tvm] jwfromm commented on pull request #7698: [TVMC] Python Scripting Init Files

jwfromm commented on pull request #7698: URL: https://github.com/apache/tvm/pull/7698#issuecomment-804449105 @merrymercy this PR is failing with this error message `AttributeError: module 'tvm.auto_scheduler._ffi_api' has no attribute 'RandomModel'`, which almost certainly isn't caused by

[GitHub] [tvm] mbaret commented on pull request #7564: [BYOC] Exclude external params from Graph Runtime

mbaret commented on pull request #7564: URL: https://github.com/apache/tvm/pull/7564#issuecomment-804438979 Ping @comaniac @zhiics, what can we do to make progress here? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[tvm] branch main updated (e4b3e90 -> 43ec869)

This is an automated email from the ASF dual-hosted git repository. kevinthesun pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git. from e4b3e90 [CI] Improve docker/build.sh to accept a docker tag parameter. (#7707) add 43ec869 Fix graph_tuner

[GitHub] [tvm] kevinthesun commented on pull request #7704: Fix graph_tuner ancestor duplication

kevinthesun commented on pull request #7704: URL: https://github.com/apache/tvm/pull/7704#issuecomment-804417292 Thanks @ambroise-arm -- 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] kevinthesun merged pull request #7704: Fix graph_tuner ancestor duplication

kevinthesun merged pull request #7704: URL: https://github.com/apache/tvm/pull/7704 -- 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. For queries about this service,

[GitHub] [tvm] AndrewZhaoLuo opened a new pull request #7722: [Topi, Relay] Add cumprod

AndrewZhaoLuo opened a new pull request #7722: URL: https://github.com/apache/tvm/pull/7722 Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews

[GitHub] [tvm] icemelon9 opened a new pull request #7721: [WIP] Rename TVMContext to Device

icemelon9 opened a new pull request #7721: URL: https://github.com/apache/tvm/pull/7721 See RFC in https://discuss.tvm.apache.org/t/rfc-rename-tvmcontext-to-tvmdevice/9090 Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful

[GitHub] [tvm] electriclilies commented on a change in pull request #7720: [ONNX] Onnx node tests

electriclilies commented on a change in pull request #7720: URL: https://github.com/apache/tvm/pull/7720#discussion_r599082811 ## File path: python/tvm/relay/frontend/onnx.py ## @@ -444,9 +448,15 @@ class ConvTranspose(OnnxOpConverter): @classmethod def _impl_v1(cls,

[GitHub] [tvm] electriclilies edited a comment on pull request #7438: [ONNX] Enable GPU in ONNX importer tests

electriclilies edited a comment on pull request #7438: URL: https://github.com/apache/tvm/pull/7438#issuecomment-804401474 @masahi I forgot to disable the dynamic version of the batch matmul test on cuda, it should be fixed now. -- This is an automated message from the Apache Git

[GitHub] [tvm] electriclilies commented on pull request #7438: [ONNX] Enable GPU in ONNX importer tests

electriclilies commented on pull request #7438: URL: https://github.com/apache/tvm/pull/7438#issuecomment-804401474 @masahi I forgot to disable the dynamic version of batch matmul on cuda, it should be fixed now. -- This is an automated message from the Apache Git Service. To respond to

[GitHub] [tvm] mbrookhart commented on a change in pull request #7720: [ONNX] Onnx node tests

mbrookhart commented on a change in pull request #7720: URL: https://github.com/apache/tvm/pull/7720#discussion_r599079051 ## File path: python/tvm/relay/frontend/onnx.py ## @@ -444,9 +448,15 @@ class ConvTranspose(OnnxOpConverter): @classmethod def _impl_v1(cls,

[GitHub] [tvm] electriclilies commented on a change in pull request #7720: [ONNX] Onnx node tests

electriclilies commented on a change in pull request #7720: URL: https://github.com/apache/tvm/pull/7720#discussion_r599033812 ## File path: python/tvm/relay/frontend/onnx.py ## @@ -444,9 +448,15 @@ class ConvTranspose(OnnxOpConverter): @classmethod def _impl_v1(cls,

[GitHub] [tvm] masahi commented on pull request #7438: [ONNX] Enable GPU in ONNX importer tests

masahi commented on pull request #7438: URL: https://github.com/apache/tvm/pull/7438#issuecomment-804393643 @electriclilies Can you take a look at the CI issue? -- 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] mbrookhart opened a new pull request #7720: [ONNX] Onnx node tests

mbrookhart opened a new pull request #7720: URL: https://github.com/apache/tvm/pull/7720 We've been hitting a lot of errors running models with ONNX, that has led to a lot of piecewise fixes. This is an attempt to fix the importer more broadly by running the tests onnx ships with pip

[GitHub] [tvm] electriclilies commented on pull request #7710: [DATA] DataLoader -- a universal interface for wrapping datasets from other machine learning frameworks

electriclilies commented on pull request #7710: URL: https://github.com/apache/tvm/pull/7710#issuecomment-804282772 @tqchen I'll get an RFC up soon, and @jroesch I can double check that this would work with PT data loaders. -- This is an automated message from the Apache Git Service. To

[tvm] branch main updated (318c650 -> e4b3e90)

This is an automated email from the ASF dual-hosted git repository. areusch pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git. from 318c650 Fix auto scheduler crash when set with consumers is empty (#7708) add e4b3e90 [CI] Improve

[GitHub] [tvm] areusch commented on pull request #7707: [CI] Improve docker/build.sh to accept a docker tag parameter.

areusch commented on pull request #7707: URL: https://github.com/apache/tvm/pull/7707#issuecomment-804215522 thanks @leandron the PR is 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

[GitHub] [tvm] areusch merged pull request #7707: [CI] Improve docker/build.sh to accept a docker tag parameter.

areusch merged pull request #7707: URL: https://github.com/apache/tvm/pull/7707 -- 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. For queries about this service, please

[GitHub] [tvm] leandron commented on pull request #7707: [CI] Improve docker/build.sh to accept a docker tag parameter.

leandron commented on pull request #7707: URL: https://github.com/apache/tvm/pull/7707#issuecomment-804207542 @areusch I guess this can be merged, when you have some time. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] tqchen commented on issue #7705: build tvm failed with libbacktrace.a : ld: symbol(s) not found for architecture x86_64

tqchen commented on issue #7705: URL: https://github.com/apache/tvm/issues/7705#issuecomment-804204170 Thanks @xiebaiyuan , yes it would be great to learn further about what happened in your case. -- This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [tvm] tqchen edited a comment on issue #7705: build tvm failed with libbacktrace.a : ld: symbol(s) not found for architecture x86_64

tqchen edited a comment on issue #7705: URL: https://github.com/apache/tvm/issues/7705#issuecomment-804204170 Thanks @xiebaiyuan , yes like @tkonolige said, it would be great to learn further about what happened in your case. So we can enable libbacktrace on your setup as well(which can

[GitHub] [tvm] tkonolige commented on pull request #7709: [FIX] Fix temporary allocation size in threefry

tkonolige commented on pull request #7709: URL: https://github.com/apache/tvm/pull/7709#issuecomment-804196450 I guess I could bump the test sizes, not sure what size it requires to error out though. We really need a way to check for out of bound memory access in tir. -- This is an

[GitHub] [tvm] tkonolige commented on issue #7705: build tvm failed with libbacktrace.a : ld: symbol(s) not found for architecture x86_64

tkonolige commented on issue #7705: URL: https://github.com/apache/tvm/issues/7705#issuecomment-804195166 @xiebaiyuan Can you provide more info on this so I can debug? Which compiler and linker are you using? And could you provide the full build log? -- This is an automated message from

[tvm] branch ci-docker-staging updated: try bumping synr

This is an automated email from the ASF dual-hosted git repository. areusch pushed a commit to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/ci-docker-staging by this push: new 87798bf try bumping synr

[tvm] branch main updated (21fc3bb -> 318c650)

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 21fc3bb [TOPI] Use fixed thread block size in unique op for Vulkan (#7718) add 318c650 Fix auto scheduler crash

[GitHub] [tvm] jwfromm merged pull request #7708: Fix auto scheduler crash when set with consumers is empty

jwfromm merged pull request #7708: URL: https://github.com/apache/tvm/pull/7708 -- 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. For queries about this service, please

[GitHub] [tvm] cgerum edited a comment on pull request #7694: [TORCH] Implement avg_pool1d

cgerum edited a comment on pull request #7694: URL: https://github.com/apache/tvm/pull/7694#issuecomment-804020598 ~~The builder seems to have timed out. Should I just add a fake commit to retrigger the build?~~ Ah sorry, missed your last post. The branch has been rebased. --

[GitHub] [tvm] mbrookhart commented on pull request #7718: [TOPI] Use fixed thread block size in unique op for Vulkan

mbrookhart commented on pull request #7718: URL: https://github.com/apache/tvm/pull/7718#issuecomment-804153287 Thanks @masahi -- 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

[tvm] branch main updated: [TOPI] Use fixed thread block size in unique op for Vulkan (#7718)

This is an automated email from the ASF dual-hosted git repository. mbrookhart 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 21fc3bb [TOPI] Use fixed thread block size in

[GitHub] [tvm] mbrookhart merged pull request #7718: [TOPI] Use fixed thread block size in unique op for Vulkan

mbrookhart merged pull request #7718: URL: https://github.com/apache/tvm/pull/7718 -- 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. For queries about this service, please

[GitHub] [tvm] mbaret commented on pull request #7628: [ETHOSN] Add support for Ethos-N 21.02 driver stack release.

mbaret commented on pull request #7628: URL: https://github.com/apache/tvm/pull/7628#issuecomment-804143529 Thanks @tristan-arm @Leo-arm, this is 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

[tvm] branch main updated: [ETHOSN] Add support for Ethos-N 21.02 driver stack release. (#7628)

This is an automated email from the ASF dual-hosted git repository. mbaret 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 c4b8934 [ETHOSN] Add support for Ethos-N 21.02 driver

[GitHub] [tvm] mbaret merged pull request #7628: [ETHOSN] Add support for Ethos-N 21.02 driver stack release.

mbaret merged pull request #7628: URL: https://github.com/apache/tvm/pull/7628 -- 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. For queries about this service, please

[GitHub] [tvm] echuraev commented on a change in pull request #7714: [METAL] Fix memory leaks in Metal runtime

echuraev commented on a change in pull request #7714: URL: https://github.com/apache/tvm/pull/7714#discussion_r598731541 ## File path: src/runtime/contrib/random/mt_random_engine.cc ## @@ -126,8 +126,10 @@ class RandomEngine { } else { runtime::NDArray local =

[GitHub] [tvm] tqchen commented on a change in pull request #7714: [METAL] Fix memory leaks in Metal runtime

tqchen commented on a change in pull request #7714: URL: https://github.com/apache/tvm/pull/7714#discussion_r598717260 ## File path: src/runtime/contrib/random/mt_random_engine.cc ## @@ -126,8 +126,10 @@ class RandomEngine { } else { runtime::NDArray local =

[GitHub] [tvm] tqchen commented on a change in pull request #7714: [METAL] Fix memory leaks in Metal runtime

tqchen commented on a change in pull request #7714: URL: https://github.com/apache/tvm/pull/7714#discussion_r598716824 ## File path: src/runtime/metal/metal_device_api.mm ## @@ -147,102 +155,110 @@ int GetWarpSize(id dev) { void* MetalWorkspace::AllocDataSpace(TVMContext

[tvm] branch main updated (fffed0f -> 4b528de)

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 fffed0f [TensorIR] TVMScript Parser/Printer (#7630) add 4b528de [TensorIR] add TIRTextPrinter support for Block

[GitHub] [tvm] tqchen merged pull request #7716: [TensorIR] add TIRTextPrinter support for Block and BlockRealize

tqchen merged pull request #7716: URL: https://github.com/apache/tvm/pull/7716 -- 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. For queries about this service, please

[GitHub] [tvm] cgerum commented on pull request #7694: [TORCH] Implement avg_pool1d

cgerum commented on pull request #7694: URL: https://github.com/apache/tvm/pull/7694#issuecomment-804020598 The builder seems to have timed out. Should I just add a fake commit to retrigger the build? -- This is an automated message from the Apache Git Service. To respond to the

[GitHub] [tvm] liaopeiyuan commented on pull request #7719: _fix_outputs for BatchNormalization

liaopeiyuan commented on pull request #7719: URL: https://github.com/apache/tvm/pull/7719#issuecomment-803943121 yes, I will add it shortly. -- 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] FrozenGene commented on pull request #7719: _fix_outputs for BatchNormalization

FrozenGene commented on pull request #7719: URL: https://github.com/apache/tvm/pull/7719#issuecomment-803942605 Thanks for contributing @liaopeiyuan However, I think it is better to add one unit testing case. Do you think so? -- This is an automated message from the Apache Git Service.

[GitHub] [tvm] liaopeiyuan commented on pull request #7719: _fix_outputs for BatchNormalization

liaopeiyuan commented on pull request #7719: URL: https://github.com/apache/tvm/pull/7719#issuecomment-803908672 @Huyuwei @siju-samuel @FrozenGene -- 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] liaopeiyuan opened a new pull request #7719: _fix_outputs for BatchNormalization

liaopeiyuan opened a new pull request #7719: URL: https://github.com/apache/tvm/pull/7719 In newer versions of ONNX (e.g. torch.onnx outputs), BatchNormalization has multiple outputs when training mode is enabled. This is a quick fix similar to the one done for Dropout. -- This is

[GitHub] [tvm] masahi opened a new pull request #7718: [TOPI] Use fixed thread block size in unique op for Vulkan

masahi opened a new pull request #7718: URL: https://github.com/apache/tvm/pull/7718 -- 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. For queries about this service,

[GitHub] [tvm] masahi opened a new pull request #7717: [Vulkan] Support uniform buffer object for passing many scalar arguments

masahi opened a new pull request #7717: URL: https://github.com/apache/tvm/pull/7717 -- 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. For queries about this service,