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

[TOPI] Fix tuple unpacking in conv2d int8 compute #13566

Merged
merged 5 commits into from
Dec 7, 2022

Conversation

michalpiszczek
Copy link
Contributor

@michalpiszczek michalpiszczek commented Dec 6, 2022

  • Fix mismatch in expected unpacked values

@tvm-bot
Copy link
Collaborator

tvm-bot commented Dec 6, 2022

Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.

  • No users to tag found in teams: topi See #10317 for details
  • Built docs for commit d98532c can be found here.

Generated by tvm-bot

@michalpiszczek michalpiszczek changed the title [TOPI] Fix tuple un-packing in Conv2d Int8 Compute [TOPI] Fix tuple unpacking in conv2d int8 compute Dec 6, 2022
@michalpiszczek
Copy link
Contributor Author

cc @jfromm

Copy link
Contributor

@jwfromm jwfromm left a comment

Choose a reason for hiding this comment

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

LGTM.

@michalpiszczek
Copy link
Contributor Author

@tvm-bot rerun

@mehrdadh
Copy link
Member

mehrdadh commented Dec 6, 2022

@michalpiszczek you need to rebase because of 9374738

@jwfromm jwfromm merged commit da73295 into apache:main Dec 7, 2022
junrushao pushed a commit that referenced this pull request Jan 17, 2023
Fixes a tuple being incorrectly unpacked (too many elements expected) in a Conv2D TOPI int8 op, similarly to #13566 which addressed the issue specifically in the ARM implementation (which calls the function modified in this PR). 

This explicit unpacking helps improve flexibility with other incoming layouts.
fzi-peccia pushed a commit to fzi-peccia/tvm that referenced this pull request Mar 27, 2023
Fixes a tuple being incorrectly unpacked (too many elements expected) in a Conv2D TOPI int8 op, similarly to apache#13566 which addressed the issue specifically in the ARM implementation (which calls the function modified in this PR). 

This explicit unpacking helps improve flexibility with other incoming layouts.
mikeseven pushed a commit to mikeseven/tvm that referenced this pull request Sep 27, 2023
* Remove mutable defaults in mlp_model

* Fix tuple unpack in conv2d nchw int8
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.

4 participants