Fix Qwen3 ONNX export bug related to 0/1 specialization - #213
Open
victoroliv2 wants to merge 1 commit into
Open
victoroliv2 wants to merge 1 commit into
victoroliv2 wants to merge 1 commit into
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
**Type of change: ** Bug Fix
In PyTorch 2.7 (version I am using), Dynamic batching in ONNX export is broken with dimension 0/1. I believe this has been fixed in pytorch/pytorch#184837
This PR fixes this issue by using dim = 2 so Qwen3 ONNX export works on older PyTorch releases (my use case).
Overview: ?
Usage
# Add a code snippet demonstrating how to use this🚀 Pull Request Checklist
Thank you for contributing to TensorRT Edge-LLM! Before we review your pull request, please make sure the following items are complete.
Please also refer to Contributor guidelines for general guidelines.
✅ Pre-commit Checks
pre-commitby runningpip install pre-commit.pre-commit install.pre-commit run --all-filesand fixed any reported issues.🧪 Tests
📄 Documentation
⚙️ Compatibility
Additional Information