Use DYNAMIC on batch size #213
Merged
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
Collaborator
Author
|
Check URLs / build (pull_request) seems buggy to me. |
xadupre
approved these changes
Sep 4, 2025
justinchuby
approved these changes
Sep 4, 2025
This reverts commit 6983c2c.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
With the current regression on 20-ish LLMs, it's found that torch.export.Dim("batch", min=1, max=1024) sets a constraints to the graph when the tracing inputs have at least 2 on batch size. While with torch.export.Dim.DYNAMIC, such constraints are not set. From ONNX perspective, we don't have constraint range, so I think it makes sense that we only use DYNAMIC in such cases.