-
Notifications
You must be signed in to change notification settings - Fork 25.7k
[ONNX] Fix sequence handling in graph building #138656
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[ONNX] Fix sequence handling in graph building #138656
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/138656
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 10b8e60 with merge base 39bfba3 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks - would it be possible to create unit tests for this? Could you share more on how you discovered this?
|
I was testing SmolLM_1_7b on benchmarking: |
|
nit: I updated the PR description for it to be more descriptive. |
I will update a small e2e test in this PR. |
|
I would like to merge this first. I will have the test as follow up. |
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Previous to this PR, op.Concat is called without required attributes: axis, and val and arg seems wrongly coded. Pull Request resolved: #138656 Approved by: https://github.com/justinchuby
Previous to this PR, op.Concat is called without required attributes: axis, and val and arg seems wrongly coded.