Skip to content

[Quantization]: Update simulated_quantize to infer correct layout#14875

Merged
masahi merged 1 commit intoapache:mainfrom
f2013519:main
May 18, 2023
Merged

[Quantization]: Update simulated_quantize to infer correct layout#14875
masahi merged 1 commit intoapache:mainfrom
f2013519:main

Conversation

@f2013519
Copy link
Copy Markdown
Contributor

In our BYOC flow, we invoke the Convert Layout pass after simulated_quantize annotations are inserted in the IR.

However, after Convert Layout, we observe layout transforms to the original layout are inserted before the simulated_quantize annotations, as the compiler is currently unable to infer the layouts from the input.

This PR allows propagation of the input layouts to avoid the insertion of additional layout transforms.

@tvm-bot
Copy link
Copy Markdown
Collaborator

tvm-bot commented May 17, 2023

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: quantization See #10317 for details

Generated by tvm-bot

@f2013519
Copy link
Copy Markdown
Contributor Author

cc: @junrushao @masahi @vinx13

@masahi masahi merged commit 28e9801 into apache:main May 18, 2023
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.

3 participants