[GitHub] [tvm] apivovarov commented on issue #8876: Unit Test java GPU failed - java.io.IOException: java.lang.RuntimeException: Failed to serialize

apivovarov commented on issue #8876: URL: https://github.com/apache/tvm/issues/8876#issuecomment-907730988 CI Build 9 failed too - https://ci.tlcpack.ai/blue/organizations/jenkins/tvm/detail/PR-8860/9/pipeline Looks like TVM CI is broken. @tqchen -- This is an automated message

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697954723 ## File path: python/tvm/contrib/pipeline_executor.py ## @@ -0,0 +1,352 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697946280 ## File path: python/tvm/contrib/pipeline_executor.py ## @@ -0,0 +1,352 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697945743 ## File path: python/tvm/contrib/pipeline_executor.py ## @@ -0,0 +1,352 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697945477 ## File path: python/tvm/contrib/pipeline_executor.py ## @@ -0,0 +1,352 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697945255 ## File path: src/runtime/pipeline/pipeline_executor.cc ## @@ -0,0 +1,49 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697945164 ## File path: tests/python/relay/test_pipeline_executor.py ## @@ -0,0 +1,256 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697945139 ## File path: tests/python/relay/test_pipeline_executor.py ## @@ -0,0 +1,256 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] comaniac commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

comaniac commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697926981 ## File path: python/tvm/contrib/pipeline_executor.py ## @@ -0,0 +1,352 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] junrushao1994 commented on pull request #8875: [TIR] GetBlockReadWriteRegion

junrushao1994 commented on pull request #8875: URL: https://github.com/apache/tvm/pull/8875#issuecomment-907698556 CC @Hzfengsy please review :-) -- 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

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697923152 ## File path: tests/python/relay/test_pipeline_executor.py ## @@ -0,0 +1,256 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697915244 ## File path: tests/python/relay/test_pipeline_executor.py ## @@ -0,0 +1,256 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] huajsj commented on a change in pull request #8702: [Runtime] Pipeline Executor Initial patch.

huajsj commented on a change in pull request #8702: URL: https://github.com/apache/tvm/pull/8702#discussion_r697914291 ## File path: tests/python/relay/test_pipeline_executor.py ## @@ -0,0 +1,256 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[tvm] branch main updated (0961b65 -> 2545e9c)

This is an automated email from the ASF dual-hosted git repository. junrushao pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git. from 0961b65 [Tutorial][Executor] Fix the usage of executors in tutorials (#8586) add 2545e9c [Frontend][Onnx]

[GitHub] [tvm] junrushao1994 merged pull request #8867: [Frontend][Onnx] Simplify onnx input since name accesses are not reliable.

junrushao1994 merged pull request #8867: URL: https://github.com/apache/tvm/pull/8867 -- 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] junrushao1994 commented on pull request #8863: [TensorIR][M2a] CacheRead/Write

junrushao1994 commented on pull request #8863: URL: https://github.com/apache/tvm/pull/8863#issuecomment-907675668 Will review tomorrow. Thanks a lot! -- 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

[GitHub] [tvm] thecooltechguy opened a new issue #8877: NotImplementedError: The following operators are not implemented: ['aten::stft']

thecooltechguy opened a new issue #8877: URL: https://github.com/apache/tvm/issues/8877 Hi, When I try to compile a Pytorch model that uses `torch.stft`, I'm getting the following error. `NotImplementedError: The following operators are not implemented: ['aten::stft']`

[GitHub] [tvm] apivovarov opened a new issue #8876: Unit Test java GPU failed - java.io.IOException: java.lang.RuntimeException: Failed to serialize

apivovarov opened a new issue #8876: URL: https://github.com/apache/tvm/issues/8876 I tried to build my PR several times. CI is unstable. Last error : `java.io.IOException: java.lang.RuntimeException: Failed to serialize hudson.model.Actionable#actions for class

[GitHub] [tvm] jwfromm edited a comment on pull request #8867: [Frontend][Onnx] Simplify onnx input since name accesses are not reliable.

jwfromm edited a comment on pull request #8867: URL: https://github.com/apache/tvm/pull/8867#issuecomment-907659234 Onnx has strict conventions around input ordering. Any optional input that isnt used, but has other inputs after it that are used, must be provided and have its name set to

[GitHub] [tvm] jwfromm edited a comment on pull request #8867: [Frontend][Onnx] Simplify onnx input since name accesses are not reliable.

jwfromm edited a comment on pull request #8867: URL: https://github.com/apache/tvm/pull/8867#issuecomment-907659234 Onnx has strict conventions around input ordering. Any optional input that isnt used, but has other inputs after it that are used, must explicitly be set to None. If this

[GitHub] [tvm] jwfromm commented on pull request #8867: [Frontend][Onnx] Simplify onnx input since name accesses are not reliable.

jwfromm commented on pull request #8867: URL: https://github.com/apache/tvm/pull/8867#issuecomment-907659234 Onnx has strict conventions around input ordering. Any optional input that isnt used, but has other inputs after it that are used, must explicitly be set to None. If this

[GitHub] [tvm] MasterJH5574 opened a new pull request #8875: [TIR] GetBlockReadWriteRegion

MasterJH5574 opened a new pull request #8875: URL: https://github.com/apache/tvm/pull/8875 This PR adds a new analysis function named `GetBlockReadWriteRegion` for TIR, which collects all buffer regions that a given block reads from and writes to. Before this PR, there was an

[GitHub] [tvm] areusch commented on a change in pull request #8738: [microTVM][RVM] Improve base-box-tool 'build' command

areusch commented on a change in pull request #8738: URL: https://github.com/apache/tvm/pull/8738#discussion_r697882277 ## File path: apps/microtvm/reference-vm/base-box-tool.py ## @@ -226,18 +227,33 @@ def generate_packer_config(file_path, providers): def

[GitHub] [tvm-rfcs] areusch commented on pull request #15: [RFC] Use CMSIS-NN with TVM

areusch commented on pull request #15: URL: https://github.com/apache/tvm-rfcs/pull/15#issuecomment-907639183 Merging as Cody said LGTM in his last review -- 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-rfcs] areusch merged pull request #15: [RFC] Use CMSIS-NN with TVM

areusch merged pull request #15: URL: https://github.com/apache/tvm-rfcs/pull/15 -- 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:

[tvm-rfcs] branch main updated: [RFC] Use CMSIS-NN with TVM (#15)

This is an automated email from the ASF dual-hosted git repository. areusch pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/tvm-rfcs.git The following commit(s) were added to refs/heads/main by this push: new 39124b1 [RFC] Use CMSIS-NN with TVM (#15)

[GitHub] [tvm-rfcs] areusch commented on a change in pull request #7: [UnitTests] Parametrized Unit Tests

areusch commented on a change in pull request #7: URL: https://github.com/apache/tvm-rfcs/pull/7#discussion_r697878666 ## File path: rfcs/0007-parametrized-unit-tests.md ## @@ -0,0 +1,568 @@ +- Feature Name: Parametrized Unit Tests +- Start Date: 2021-05-10(fill me in with

[GitHub] [tvm] manupa-arm commented on issue #8717: Fusion of operations and cast in mobilenet v1 conv2d causing large feature maps

manupa-arm commented on issue #8717: URL: https://github.com/apache/tvm/issues/8717#issuecomment-907621658 Hi All, Thanks for looking at this, for the relay please check the relay in 'Primitive' form (not the relay that goes on relay.build). This relay could be found at observing

[GitHub] [tvm] junrushao1994 commented on pull request #8586: [Tutorial][Executor] Fix the usage of executors in tutorials

junrushao1994 commented on pull request #8586: URL: https://github.com/apache/tvm/pull/8586#issuecomment-907600180 Thanks @ganler! It is finally 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

[tvm] branch main updated: [Tutorial][Executor] Fix the usage of executors in tutorials (#8586)

This is an automated email from the ASF dual-hosted git repository. junrushao 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 0961b65 [Tutorial][Executor] Fix the usage of

[GitHub] [tvm] junrushao1994 merged pull request #8586: [Tutorial][Executor] Fix the usage of executors in tutorials

junrushao1994 merged pull request #8586: URL: https://github.com/apache/tvm/pull/8586 -- 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:

[tvm] branch main updated (7214f52 -> 5ab527a)

This is an automated email from the ASF dual-hosted git repository. junrushao pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git. from 7214f52 [TIR] Fix opaque access in buffer locator pass and match_buffer in region detector (#8855) add 5ab527a

[tvm] branch main updated: [TIR] Fix opaque access in buffer locator pass and match_buffer in region detector (#8855)

This is an automated email from the ASF dual-hosted git repository. junrushao 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 7214f52 [TIR] Fix opaque access in buffer locator

[GitHub] [tvm] junrushao1994 merged pull request #8862: [Autoscheduler] Configurable workload keys

junrushao1994 merged pull request #8862: URL: https://github.com/apache/tvm/pull/8862 -- 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] junrushao1994 merged pull request #8855: [TIR] Fix opaque access in buffer locator pass and match_buffer in region detector

junrushao1994 merged pull request #8855: URL: https://github.com/apache/tvm/pull/8855 -- 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] junrushao1994 commented on pull request #8871: [Build] Generate libinfo.cc

junrushao1994 commented on pull request #8871: URL: https://github.com/apache/tvm/pull/8871#issuecomment-907596657 I believe @antinucleon has some experience (painfully) migrating python to C++ :-) -- This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [tvm] AriMIR commented on issue #8717: Fusion of operations and cast in mobilenet v1 conv2d causing large feature maps

AriMIR commented on issue #8717: URL: https://github.com/apache/tvm/issues/8717#issuecomment-907596350 Hello @Mousius, Sorry for the large number of questions. I just started to deal with the mechanics of TVM and it is quite possible that some of the questions are pretty stupid.