[Quantization]: Update simulated_quantize to infer correct layout#14875
Merged
masahi merged 1 commit intoapache:mainfrom May 18, 2023
f2013519:main
Merged
[Quantization]: Update simulated_quantize to infer correct layout#14875masahi merged 1 commit intoapache:mainfrom f2013519:main
masahi merged 1 commit intoapache:mainfrom
f2013519:main
Conversation
Collaborator
|
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.
Generated by tvm-bot |
Contributor
Author
|
cc: @junrushao @masahi @vinx13 |
masahi
approved these changes
May 18, 2023
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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.