Repository navigation
Fix CPU Conv1D dilation and INT8 scale overflow - #2117
Merged
jordimas merged 2 commits intoOct 19, 2026
Merged
Conversation
jordimas
commented
Oct 18, 2026
jordimas
commented
Collaborator
- Align CPU Conv1D implementations: correct oneDNN dilation and add matching GEMM support. Test dilation, padding, stride, and bias against explicit expected outputs.
- Bound INT8 scales for tiny nonzero weight rows: float32 division can overflow before rounding, causing invalid arithmetic. Add a regression test checking finite results.
TBO22
added a commit
to TBO22/CTranslate2
that referenced
this pull request
Oct 24, 2026
Merge master again (OpenNMT#2097, OpenNMT#2117)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.