fix: guard fold_constants against 0-node graphs for CLIP's optimize() override too#17
Merged
Conversation
… override too CLIP's optimize() (models.py) overrides BaseModel.optimize() entirely and calls opt.fold_constants() directly, bypassing the 0-node guard added to BaseModel.optimize() in the prior fix (#16). Move an equivalent guard into Optimizer.fold_constants() itself so every optimize() variant -- current and future -- is covered by a single check at the one call site that actually crashes on an empty/corrupt source ONNX. Co-Authored-By: Claude Sonnet 5 <[email protected]>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #16 -- moves the 0-node guard into Optimizer.fold_constants() itself since CLIP's optimize() override bypasses BaseModel.optimize()'s check. See models.py Optimizer.fold_constants(). 🤖 Generated with Claude Code