Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ONNX] Add support for QLinearConcat contrib op #8907

Merged
merged 10 commits into from
Sep 8, 2021

Conversation

anwang2009
Copy link
Contributor

  • Moves get_scalar to common point where other Q op impls can reach it.
  • Adds QLinearConcat
  • Note the Lowering function within _qnn.op.concatenate will requantize as necessary, so there is nothing special necessary that needs to be done here for this Q op.

@anwang2009
Copy link
Contributor Author

cc @AndrewZhaoLuo @mbrookhart

Copy link
Contributor

@AndrewZhaoLuo AndrewZhaoLuo left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A few comments but LGTM

python/tvm/relay/frontend/onnx.py Show resolved Hide resolved
python/tvm/relay/frontend/onnx.py Show resolved Hide resolved
tests/python/frontend/onnx/test_forward.py Outdated Show resolved Hide resolved
@tmoreau89
Copy link
Contributor

Awesome to see this thank you @anwang2009 ! Could you add the [ONNX] tag to the PR? Thank you!

@anwang2009 anwang2009 changed the title Add support for QLinearConcat contrib op [ONNX] Add support for QLinearConcat contrib op Sep 3, 2021
Copy link
Contributor

@mbrookhart mbrookhart left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. Looks like you hit a flaky test, try relaunching CI?

Copy link
Contributor

@tmoreau89 tmoreau89 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM thank you!

@tmoreau89
Copy link
Contributor

It seems we have a CI error which I'm not sure relates to the PR at all:

java.io.IOException: java.lang.RuntimeException: Failed to serialize hudson.model.Actionable#actions for class org.jenkinsci.plugins.workflow.job.WorkflowRun

@AndrewZhaoLuo
Copy link
Contributor

It seems we have a CI error which I'm not sure relates to the PR at all:

java.io.IOException: java.lang.RuntimeException: Failed to serialize hudson.model.Actionable#actions for class org.jenkinsci.plugins.workflow.job.WorkflowRun

If you jostle ci via git commit -m "jostle ci" --allow-empty` and push it should restart it. It's jsut something flaky with CI

@masahi masahi merged commit 475e9e0 into apache:main Sep 8, 2021
ylc pushed a commit to ylc/tvm that referenced this pull request Sep 29, 2021
* add qlinearconcat op

* fix tests

* Fix

* lint

* lint

* review

* boop ci

* fix regression

* noop

* jostle ci
ylc pushed a commit to ylc/tvm that referenced this pull request Jan 13, 2022
* add qlinearconcat op

* fix tests

* Fix

* lint

* lint

* review

* boop ci

* fix regression

* noop

* jostle ci
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants