[GitHub] [tvm] elvin-n opened a new pull request #8202: Add thread_warp_size for Metal device in default target attributes

elvin-n opened a new pull request #8202: URL: https://github.com/apache/tvm/pull/8202 Recently new transpose op strategy was added for cuda which use thread_warp_size from default target attr parameters. Since Metal fallback to cuda, it needs this parameter to be defined. The exact

[GitHub] [tvm] elvin-n opened a new pull request #8201: [TOPI] [INTEL GRAPHICS] Fix conv2d_nchw for opencl intel graphics

elvin-n opened a new pull request #8201: URL: https://github.com/apache/tvm/pull/8201 I got 0% of accurqacy with target="opencl -device=intel_graphics" on IrisXe. I found severtal issue (using warp instead of shared scope for variables) but fixed only for conv2d_nchw. conv2d_nchwc is

[GitHub] [tvm] zackcquic edited a comment on issue #4449: [RFC] Program Analysis Framework in Relay

zackcquic edited a comment on issue #4449: URL: https://github.com/apache/tvm/issues/4449#issuecomment-855587891 Hi @gussmith23: I just start playing with TVM this year. I think this is very useful to me. >I'm posting this in advance of the TVM conference this year, as I'm

[GitHub] [tvm] zackcquic commented on issue #4449: [RFC] Program Analysis Framework in Relay

zackcquic commented on issue #4449: URL: https://github.com/apache/tvm/issues/4449#issuecomment-855587891 Hi @gussmith23: I just start playing with TVM this year. I'd think this is very useful to me. >I'm posting this in advance of the TVM conference this year, as I'm doing

[GitHub] [tvm] zackcquic commented on issue #4468: [RFC] Data-flow Analysis Functionality on TVM IR

zackcquic commented on issue #4468: URL: https://github.com/apache/tvm/issues/4468#issuecomment-855578430 Hi: I am wondering if there is any update on this proposal (after IR unified)? -- This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [tvm] jcf94 commented on pull request #8103: Auto-tuning a Convolutional Network for ARM CPU (tutorial error, bug reports)

jcf94 commented on pull request #8103: URL: https://github.com/apache/tvm/pull/8103#issuecomment-855524425 @cbswj Hi, it nees you to fix the lint error following the `https://ci.tlcpack.ai/blue/organizations/jenkins/tvm/detail/PR-8103/2/pipeline` before we can merge this. I can

[GitHub] [tvm] vinx13 commented on issue #8123: GPU result is different from CPU

vinx13 commented on issue #8123: URL: https://github.com/apache/tvm/issues/8123#issuecomment-855507920 Thanks for asking the question, please open a new thread on https://discuss.tvm.apache.org/ as we use the forum for related discussions. Could you try to identify which operator goes

[GitHub] [tvm] vinx13 closed issue #8123: GPU result is different from CPU

vinx13 closed issue #8123: URL: https://github.com/apache/tvm/issues/8123 -- 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 contact

[GitHub] [tvm] ZihengJiang commented on a change in pull request #8200: [RUNTIME] ShapeTuple Container

ZihengJiang commented on a change in pull request #8200: URL: https://github.com/apache/tvm/pull/8200#discussion_r646215772 ## File path: include/tvm/runtime/container/shape_tuple.h ## @@ -0,0 +1,96 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or

[GitHub] [tvm] vinx13 commented on issue #8145: Auto-scheduler tuned OpenCL kernel produces Invalid Workgroup Size Error

vinx13 commented on issue #8145: URL: https://github.com/apache/tvm/issues/8145#issuecomment-855507092 Thanks for asking the question, please open a new thread on https://discuss.tvm.apache.org/ as we use the forum for related discussions. For this case, could you if check hardware params

[GitHub] [tvm] vinx13 closed issue #8145: Auto-scheduler tuned OpenCL kernel produces Invalid Workgroup Size Error

vinx13 closed issue #8145: URL: https://github.com/apache/tvm/issues/8145 -- 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 contact

[GitHub] [tvm] ZihengJiang opened a new pull request #8200: [RUNTIME] ShapeTuple Container

ZihengJiang opened a new pull request #8200: URL: https://github.com/apache/tvm/pull/8200 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] vinx13 edited a comment on issue #8159: [TVM] Build TVM runtime results into segmentation fault

vinx13 edited a comment on issue #8159: URL: https://github.com/apache/tvm/issues/8159#issuecomment-855499949 Thanks for asking the question, please open a new thread on https://discuss.tvm.apache.org/ as we use the forum for related discussions. If error occurred in

[GitHub] [tvm] vinx13 commented on issue #8159: [TVM] Build TVM runtime results into segmentation fault

vinx13 commented on issue #8159: URL: https://github.com/apache/tvm/issues/8159#issuecomment-855499949 Thanks for asking the question, please open a new thread on https://discuss.tvm.apache.org/ as we use the forum for related discussions. If error occurred in `tvm::runtime::Module mod

[GitHub] [tvm] vinx13 closed issue #8159: [TVM] Build TVM runtime results into segmentation fault

vinx13 closed issue #8159: URL: https://github.com/apache/tvm/issues/8159 -- 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 contact

[GitHub] [tvm] abuvaneswari commented on issue #7204: mesg: ttyname failed: Inappropriate ioctl for device

abuvaneswari commented on issue #7204: URL: https://github.com/apache/tvm/issues/7204#issuecomment-855461631 I am considering buying Alveo U50 and following the VTA workflow. Can someone let me know if Alveo U50 is compatible with VTA? It is one of the supported PYNQ boards as you can see

[tvm] branch main updated: Fix incorrect device name in TVMC. (#8181)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/main by this push: new 072a3d2 Fix incorrect device name in TVMC. (#8181)

[GitHub] [tvm] masahi merged pull request #8181: Fix incorrect device name in TVMC.

masahi merged pull request #8181: URL: https://github.com/apache/tvm/pull/8181 -- 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

[tvm] branch main updated: [CI][DOCS] Fix the sphinx doc style for sphinx4 (#8198)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/main by this push: new f4b5e76 [CI][DOCS] Fix the sphinx doc style for

[GitHub] [tvm] masahi merged pull request #8198: [CI][DOCS] Fix the sphinx doc style for sphinx4

masahi merged pull request #8198: URL: https://github.com/apache/tvm/pull/8198 -- 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] kevinLu1114 commented on a change in pull request #6700: [Relay][Frontend][Onnx] Loop Support

kevinLu1114 commented on a change in pull request #6700: URL: https://github.com/apache/tvm/pull/6700#discussion_r646167029 ## File path: python/tvm/relay/frontend/onnx.py ## @@ -1995,6 +2022,164 @@ def _impl_v11(cls, inputs, attr, params): return result +class

[GitHub] [tvm] kevinLu1114 commented on a change in pull request #6700: [Relay][Frontend][Onnx] Loop Support

kevinLu1114 commented on a change in pull request #6700: URL: https://github.com/apache/tvm/pull/6700#discussion_r646167029 ## File path: python/tvm/relay/frontend/onnx.py ## @@ -1995,6 +2022,164 @@ def _impl_v11(cls, inputs, attr, params): return result +class

[tvm] branch main updated (2cca934 -> cc9d5cf)

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 2cca934 [RUNTIME][REFACTOR] Re-organize Containers into SubFolders (#8183) add cc9d5cf update python code style

[GitHub] [tvm] tqchen merged pull request #8199: Update python code style to 3.6

tqchen merged pull request #8199: URL: https://github.com/apache/tvm/pull/8199 -- 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] tqchen merged pull request #8183: [RUNTIME][REFACTOR] Re-organize Containers into SubFolders

tqchen merged pull request #8183: URL: https://github.com/apache/tvm/pull/8183 -- 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] stoa edited a comment on pull request #7742: Contributing the STM32 port

stoa edited a comment on pull request #7742: URL: https://github.com/apache/tvm/pull/7742#issuecomment-855391490 @areusch @tqchen Hello, Let then sort out the review feedback in the order of importance: > I'd like to avoid merging an alternative implementation of

[GitHub] [tvm] liaopeiyuan edited a comment on pull request #7719: _fix_outputs for BatchNormalization

liaopeiyuan edited a comment on pull request #7719: URL: https://github.com/apache/tvm/pull/7719#issuecomment-855392525 -- 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

[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-855392525 Does the onnxruntime build on CI come with training mode enabled? Seems like the problem is onnxruntime being unhappy with batchnorm containing multiple outputs wuile

[GitHub] [tvm] stoa commented on pull request #7742: Contributing the STM32 port

stoa commented on pull request #7742: URL: https://github.com/apache/tvm/pull/7742#issuecomment-855391490 @areusch @tqchen Hello, Let then sort out the review feedback in the order of importance: > I'd like to avoid merging an alternative implementation of

[GitHub] [tvm] liaopeiyuan opened a new pull request #8199: Update python code style to 3.6

liaopeiyuan opened a new pull request #8199: URL: https://github.com/apache/tvm/pull/8199 Per `python/tvm/_ffi/_pyversion.py`, it seems like the minimal Python requirement is Python 3.6 -- This is an automated message from the Apache Git Service. To respond to the message, please log on