[x86] Fix missing fake metadata in quantized concat linear CPU fusion#4508
Draft
Yuxingwang-intel wants to merge 1 commit into
Draft
[x86] Fix missing fake metadata in quantized concat linear CPU fusion#4508Yuxingwang-intel wants to merge 1 commit into
Yuxingwang-intel wants to merge 1 commit into
Conversation
Yuxingwang-intel
requested review from
Valentine233 and
Xia-Weiwen
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/4508
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds fake tensor metadata for the fused qlinear node created by the quantized concat linear CPU fusion pass.
The pass replaces multiple qlinear nodes with one fused qlinear node followed by split_with_sizes. Since the new qlinear node is manually created, it does not automatically carry meta["val"]. Without this metadata, FakeTensorUpdater may treat the fused qlinear output as None when updating the following split_with_sizes node.
The fused output shape is inferred from the original qlinear users.