onnx: add com.microsoft SkipLayerNormalization handler#2289
Merged
Conversation
czoli1976
force-pushed
the
feature/onnx-skiplayernorm
branch
from
834ba9f to
388d890
Compare
kali
previously approved these changes
May 27, 2026
Collaborator
|
need a rebase here... |
Residual (input + skip + bias) followed by LayerNormalization over the last axis scaled by gamma (+ beta), computed in f32. Optionally emits mean / inv_std_var / input_skip_bias_sum outputs. Validated bit-close against onnxruntime (output + input_skip_bias_sum). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
czoli1976
force-pushed
the
feature/onnx-skiplayernorm
branch
from
388d890 to
f78d791
Compare
Contributor
Author
|
done, rebased |
kali
approved these changes
May 27, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
SkipLayerNormalization: residual (input+skip+bias) then LayerNormalization over the last axis scaled by gamma (+beta), computed in f32, with optional mean/inv_std_var/input_skip_bias_sum outputs. Validated bit-close vs onnxruntime across beta/bias/present-output combinations and shapes; no node-suite regression; clippy+fmt clean. Part of com.microsoft contrib-op coverage for ORT-exported LLMs.