[GitHub] [incubator-tvm] zhiics commented on issue #6629: Cuda NMS argsorts with invalid entries

zhiics commented on issue #6629: URL: https://github.com/apache/incubator-tvm/issues/6629#issuecomment-704009824 cc @Laurawly This is an automated message from the Apache Git Service. To respond to the message, please log

[GitHub] [incubator-tvm] tkonolige commented on a change in pull request #6580: Faster sparse_dense on GPUs

tkonolige commented on a change in pull request #6580: URL: https://github.com/apache/incubator-tvm/pull/6580#discussion_r499745730 ## File path: python/tvm/tir/ir_builder.py ## @@ -74,8 +75,23 @@ def asobject(self): def dtype(self): return self._content_type +

[incubator-tvm] branch ci-docker-staging updated (c3fffe9 -> f8c298b)

This is an automated email from the ASF dual-hosted git repository. moreau pushed a change to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from c3fffe9 fix jenkins syntax hopefully add f8c298b one last syntax error No new revisions

[GitHub] [incubator-tvm] areusch opened a new pull request #6630: [µTVM] Avoid use of builtin math functions

areusch opened a new pull request #6630: URL: https://github.com/apache/incubator-tvm/pull/6630 Fixes `undefined reference to \`expf'` errors This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated: [FIX, AUTOTVM] Print warning when all autotvm tasks fail with errors (#6612)

This is an automated email from the ASF dual-hosted git repository. comaniac pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/master by this push: new 86122d1 [FIX,AUTOTVM] Print warning

[GitHub] [incubator-tvm] comaniac commented on pull request #6612: [FIX,AUTOTVM] Print warning when all autotvm tasks fail with errors

comaniac commented on pull request #6612: URL: https://github.com/apache/incubator-tvm/pull/6612#issuecomment-703948589 Thanks @tkonolige This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] comaniac merged pull request #6612: [FIX,AUTOTVM] Print warning when all autotvm tasks fail with errors

comaniac merged pull request #6612: URL: https://github.com/apache/incubator-tvm/pull/6612 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] [incubator-tvm] Hecmay opened a new issue #6634: [Anosr][Bug] ValueError: arch(sm_xy) is not passed, and we cannot detect it from env

Hecmay opened a new issue #6634: URL: https://github.com/apache/incubator-tvm/issues/6634 ## Environment * Ubuntu 18.04.5 LTS * CUDA Version: 11.0. * GPU: RTX 2080 Ti. Compute Compatibility : 7.5 ## Description I created a simple MatMul tensor expression in C++, and

[incubator-tvm] branch ci-docker-staging updated (f8c298b -> d901d58)

This is an automated email from the ASF dual-hosted git repository. moreau pushed a change to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from f8c298b one last syntax error add d901d58 Add ci_qemu to Jenkinsfile No new revisions were

[GitHub] [incubator-tvm] hogepodge commented on issue #6623: [RFC] Move to use main as default branch

hogepodge commented on issue #6623: URL: https://github.com/apache/incubator-tvm/issues/6623#issuecomment-703897640 This change would be in accordance with the [Apache Code of Conduct](https://www.apache.org/foundation/policies/conduct.html) across several dimensions. 1. It creates

[GitHub] [incubator-tvm] mbrookhart commented on a change in pull request #6533: Scatter on Cuda

mbrookhart commented on a change in pull request #6533: URL: https://github.com/apache/incubator-tvm/pull/6533#discussion_r499881267 ## File path: python/tvm/topi/cuda/scatter.py ## @@ -0,0 +1,444 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] tmoreau89 commented on pull request #6626: Fix a bug with Alter Op Layout

tmoreau89 commented on pull request #6626: URL: https://github.com/apache/incubator-tvm/pull/6626#issuecomment-703949576 Thank you @mbrookhart @jwfromm the PR has been merged. This is an automated message from the Apache Git

[incubator-tvm] branch master updated: Fix a bug with Alter Op Layout (#6626)

This is an automated email from the ASF dual-hosted git repository. moreau pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/master by this push: new 311eca4 Fix a bug with Alter Op Layout

[GitHub] [incubator-tvm] tmoreau89 merged pull request #6626: Fix a bug with Alter Op Layout

tmoreau89 merged pull request #6626: URL: https://github.com/apache/incubator-tvm/pull/6626 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] [incubator-tvm] jroesch commented on issue #6622: [VOTE] Release Apache TVM (incubating) v0.7.0.rc0

jroesch commented on issue #6622: URL: https://github.com/apache/incubator-tvm/issues/6622#issuecomment-703882812 +1 (binding) * Checked the code compiles * Checked License and Notice * Version This is an automated

[GitHub] [incubator-tvm] jroesch commented on issue #6628: [Rust] Add MXNet to ci-cpu image to test Rust ResNet examples.

jroesch commented on issue #6628: URL: https://github.com/apache/incubator-tvm/issues/6628#issuecomment-703952444 As part of this branch we need to add Rust to GPU image so we can build Rust docs in CI. This is an automated

[GitHub] [incubator-tvm] caoqichun opened a new issue #6633: tvm.error:OpNotImplemented: The following operators are not supported for frontend ONNX: NonMaxSuppression

caoqichun opened a new issue #6633: URL: https://github.com/apache/incubator-tvm/issues/6633 Thanks for participating in the TVM community! We use https://discuss.tvm.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature

[GitHub] [incubator-tvm] tqchen edited a comment on issue #6623: [RFC] Move to use main as default branch

tqchen edited a comment on issue #6623: URL: https://github.com/apache/incubator-tvm/issues/6623#issuecomment-703171276 To be fully transparent about what it would take: - create main branch from master - setup branch protection - New PRs and other activities will continue to

[GitHub] [incubator-tvm] tmoreau89 opened a new pull request #6632: [CI] Update ci-cpu to the latest

tmoreau89 opened a new pull request #6632: URL: https://github.com/apache/incubator-tvm/pull/6632 Specifically, making sure that some of the latest changes to TVM dockerfile are taken into account: * Ethos n driver update: https://github.com/apache/incubator-tvm/pull/6606 * Vitis AI

[GitHub] [incubator-tvm] mbrookhart commented on a change in pull request #6533: Scatter on Cuda

mbrookhart commented on a change in pull request #6533: URL: https://github.com/apache/incubator-tvm/pull/6533#discussion_r499885677 ## File path: tests/python/relay/test_op_level3.py ## @@ -903,8 +904,8 @@ def verify_scatter(dshape, ishape, axis=0): indices_np =

[incubator-tvm] 01/01: add QEMU build to regression

This is an automated email from the ASF dual-hosted git repository. moreau pushed a commit to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git commit 073bc6ea8d4a18258153cd01742fbbcd7b037968 Author: Andrew Reusch AuthorDate: Mon Oct 5 15:55:02 2020

[incubator-tvm] branch ci-docker-staging updated (d901d58 -> 073bc6e)

This is an automated email from the ASF dual-hosted git repository. moreau pushed a change to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. omit d901d58 Add ci_qemu to Jenkinsfile omit f8c298b one last syntax error omit c3fffe9 fix

[GitHub] [incubator-tvm] tqchen edited a comment on issue #6623: [RFC] Move to use main as default branch

tqchen edited a comment on issue #6623: URL: https://github.com/apache/incubator-tvm/issues/6623#issuecomment-703171276 To be fully transparent about what it would take: - create main branch from master - setup branch protection - New PRs and other activities will continue to

[GitHub] [incubator-tvm] tkonolige commented on pull request #6612: [FIX,AUTOTVM] Print warning when all autotvm tasks fail with errors

tkonolige commented on pull request #6612: URL: https://github.com/apache/incubator-tvm/pull/6612#issuecomment-703937603 @comaniac CI is all green now. This is an automated message from the Apache Git Service. To respond to

[GitHub] [incubator-tvm] giuseros commented on pull request #6445: Add dot product support for quantized convolution.

giuseros commented on pull request #6445: URL: https://github.com/apache/incubator-tvm/pull/6445#issuecomment-703764060 Hi @mbaret , Thank you for the careful review! @FrozenGene , @anijain2305 should we merge this in?

[GitHub] [incubator-tvm] hogepodge commented on pull request #6625: [TVMC] fail gracefully in case no subcommand is provided

hogepodge commented on pull request #6625: URL: https://github.com/apache/incubator-tvm/pull/6625#issuecomment-703735736 lgtm, thanks! This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] tqchen commented on pull request #6603: Add µTVM Zephyr support + QEMU regression test

tqchen commented on pull request #6603: URL: https://github.com/apache/incubator-tvm/pull/6603#issuecomment-703837862 @jroesch can you help manage the PR? This is an automated message from the Apache Git Service. To respond

[GitHub] [incubator-tvm] tqchen commented on pull request #6603: Add µTVM Zephyr support + QEMU regression test

tqchen commented on pull request #6603: URL: https://github.com/apache/incubator-tvm/pull/6603#issuecomment-703838421 cc @tmoreau89 , please sync push to ci-docker-staging to confirm if docker-staging passes This is an

[GitHub] [incubator-tvm] alec-anyvision opened a new issue #6629: Cuda NMS argsorts with invalid entries

alec-anyvision opened a new issue #6629: URL: https://github.com/apache/incubator-tvm/issues/6629 I believe the following two lines should have `valid_count=valid_count`, as in [the default

[GitHub] [incubator-tvm] zhiics commented on issue #6622: [VOTE] Release Apache TVM (incubating) v0.7.0.rc0

zhiics commented on issue #6622: URL: https://github.com/apache/incubator-tvm/issues/6622#issuecomment-703743085 +1 (binding) - Checked the signature and hash - The code compiles - Checked LICESE and NOTICE This

[GitHub] [incubator-tvm] mbrookhart opened a new pull request #6626: Fix a bug with Alter Op Layout

mbrookhart opened a new pull request #6626: URL: https://github.com/apache/incubator-tvm/pull/6626 We found a case where models imported from Tensorflow in NCHW layout fail in AlterOpLayout due to an odd combination of passes. This PR adds a regression tests and short-circuits the Scalar

[GitHub] [incubator-tvm] jwfromm commented on a change in pull request #6616: [Topi] Allow batch_matmul to broadcast along batch dimension.

jwfromm commented on a change in pull request #6616: URL: https://github.com/apache/incubator-tvm/pull/6616#discussion_r499822421 ## File path: tests/python/frontend/onnx/test_forward.py ## @@ -3628,7 +3628,6 @@ def verify_roi_align( test_clip_min_max_as_inputs()

[GitHub] [incubator-tvm] tmoreau89 commented on issue #6622: [VOTE] Release Apache TVM (incubating) v0.7.0.rc0

tmoreau89 commented on issue #6622: URL: https://github.com/apache/incubator-tvm/issues/6622#issuecomment-703874194 +1 (binding): This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] tmoreau89 edited a comment on issue #6622: [VOTE] Release Apache TVM (incubating) v0.7.0.rc0

tmoreau89 edited a comment on issue #6622: URL: https://github.com/apache/incubator-tvm/issues/6622#issuecomment-703874194 This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [incubator-tvm] jroesch commented on pull request #6563: [Rust] Improve NDArray, GraphRt, and Relay bindings

jroesch commented on pull request #6563: URL: https://github.com/apache/incubator-tvm/pull/6563#issuecomment-703849631 We need to update the docker images to match MxNet see #6628 This is an automated message from the

[GitHub] [incubator-tvm] rkimball opened a new pull request #6627: Fix example code

rkimball opened a new pull request #6627: URL: https://github.com/apache/incubator-tvm/pull/6627 The example code in the comment for Object had errors This is an automated message from the Apache Git Service. To respond

[GitHub] [incubator-tvm] jroesch opened a new issue #6628: [Rust] Add MXNet to ci-cpu image to test Rust ResNet examples.

jroesch opened a new issue #6628: URL: https://github.com/apache/incubator-tvm/issues/6628 @mwillsey and I updated the ResNet example to check the correctness of the model by using a pre-trained model instead of random weights. In order to turn this on in CI we need to update the

[GitHub] [incubator-tvm] alec-anyvision opened a new issue #6631: Race Condition in Cuda SSD Multibox

alec-anyvision opened a new issue #6631: URL: https://github.com/apache/incubator-tvm/issues/6631 I may be missing something about the IR, but there seems to be a race condition in the following line. There is no guarantee that `temp_valid_count[tid * num_anchors + k - 1]` will be

[GitHub] [incubator-tvm] jroesch merged pull request #6632: [CI] Update ci-cpu to the latest

jroesch merged pull request #6632: URL: https://github.com/apache/incubator-tvm/pull/6632 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

[incubator-tvm] branch master updated: bump dockerfile (#6632)

This is an automated email from the ASF dual-hosted git repository. jroesch pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/master by this push: new feb041d bump dockerfile (#6632)

[GitHub] [incubator-tvm] m3at opened a new issue #6624: [Relay] Module mutated in-place

m3at opened a new issue #6624: URL: https://github.com/apache/incubator-tvm/issues/6624 Following [discussion on the forum](https://discuss.tvm.apache.org/t/unable-to-build-relay-function-twice/7987) I'm opening this issue for what appear to be a bug when running `relay.build`, with

[GitHub] [incubator-tvm] bgchun commented on issue #6622: [VOTE] Release Apache TVM (incubating) v0.7.0.rc0

bgchun commented on issue #6622: URL: https://github.com/apache/incubator-tvm/issues/6622#issuecomment-703514088 +1 (binding) - I checked the signature and hash. - DISCLAIMER, LICENSE, and NOTICE look good - No unexpected binary files - The code compiles and runs

[GitHub] [incubator-tvm] FrozenGene commented on issue #6622: [VOTE] Release Apache TVM (incubating) v0.7.0.rc0

FrozenGene commented on issue #6622: URL: https://github.com/apache/incubator-tvm/issues/6622#issuecomment-703569247 +1, I checked - signature and hash - LICENSE, DISCLAIMER and NOTICE - Version - Code compiles

[GitHub] [incubator-tvm] leandron opened a new pull request #6625: [TVMC] fail gracefully in case no subcommand is provided

leandron opened a new pull request #6625: URL: https://github.com/apache/incubator-tvm/pull/6625 This fixes an issue, when the user calls `tvmc` with no arguments at all. Rather than showing an `AssertError`, it now shows _usage_ and exit with code 1. @hogepodge reported it on Discuss.