[FRONTEND][ONNX] Make bias input optional in LayerNormalization #17980
Conversation
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
vacu9708
force-pushed
the
onnx_LayerNormalization
branch
from
eb90f96 to
d6f230c
Compare
Contributor
Author
|
@tvm-bot re-run |
Member
|
Would be great if you could add a testcase for it :) |
This change updates the LayerNormalization converter to support ONNX models where the optional bias input is not provided. When bias is missing, an empty bias tensor is generated. This behavior aligns with the ONNX’s spec for LayerNormalization (opset 17+) where the bias input is officially optional.
vacu9708
force-pushed
the
onnx_LayerNormalization
branch
from
d6f230c to
2eea7f8
Compare
Contributor
Author
|
@Hzfengsy |
Hzfengsy
approved these changes
May 15, 2025
ShiboXing
pushed a commit
to ShiboXing/tvm
that referenced
this pull request
Aug 10, 2025
…he#17980) This change updates the LayerNormalization converter to support ONNX models where the optional bias input is not provided. When bias is missing, an empty bias tensor is generated. This behavior aligns with the ONNX’s spec for LayerNormalization (opset 17+) where the bias input is officially optional.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Summary
This PR resolves issue #17899 where an error occurs converting operator LayerNormalization.
Reference
According to the ONNX documentation for the LayerNormalization operator (opset 17), the operator accepts between 2 and 3 inputs:
This means that the bias input (B) is optional. The operator is designed to function correctly even when the bias is not provided.
Update
This change updates the LayerNormalization converter to support ONNX models where the optional bias input is not provided. When bias is missing, an empty bias tensor is generated.