Fix LSTM clipping before h activation (Issue #27224)#27239
Open
chaya2350 wants to merge 2 commits intomicrosoft:mainfrom
Open
Fix LSTM clipping before h activation (Issue #27224)#27239chaya2350 wants to merge 2 commits intomicrosoft:mainfrom
chaya2350 wants to merge 2 commits intomicrosoft:mainfrom
Conversation
- Add clipping of Ct before applying h activation function - Complies with ONNX spec requirement for clipping input of activations - Equation: Ht = ot (.) h(clip(Ct)) instead of Ht = ot (.) h(Ct)
Author
|
@bac-cab Could you please review this PR? It fixes the issue you reported. Thanks! 🙂 |
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes Issue #27224 by implementing proper clipping of the LSTM cell state (Ct) before applying the h() activation function, as required by the ONNX specification. Previously, the cell state was passed directly to the activation function without clipping, which violated the ONNX LSTM specification.
Changes:
- Added clipping of cell state Ct before h() activation in the LSTM forward pass
- Used
clip_ignore_biasinstead ofclip_with_bias_ptr_to avoid SEGFAULT with nullptr bias - Copied Ct to temporary buffer before clipping to preserve the original value
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 fixes Issue #27224 where LSTM cell state (Ct) was not being clipped before applying the h() activation function, which violates the ONNX specification.
Changes
Testing
Related Issue
Fixes #27224