Fix constant in constant folding #2622
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
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #2622 +/- ##
==========================================
+ Coverage 69.97% 70.30% +0.33%
==========================================
Files 222 222
Lines 26324 26278 -46
Branches 2609 2625 +16
==========================================
+ Hits 18420 18476 +56
+ Misses 6992 6885 -107
- Partials 912 917 +5 ☔ View full report in Codecov by Sentry. |
xadupre
approved these changes
Oct 10, 2025
Contributor
Author
|
I will merge by the end of the day so we can catch it in the next week benchmark. |
justinchuby
changed the title
justinchuby
reviewed
Oct 10, 2025
|
|
||
| # Propagate const_value, and manually find out shape and type | ||
| # to avoid potentially expensive shape inference on large tensors. | ||
| if _is_onnx_op(node, "Constant"): |
Collaborator
There was a problem hiding this comment.
I feel that we can standardize this with other node processers, but non blocking for now.
justinchuby
approved these changes
Oct 10, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
This PR moves the processing of constant ops upward to return before node-level shape type inference (including serialization) and optimizer optimization.
Essentially, avoiding serializing constant ops (potentially large weights in LLMs) reduces the export time in optimize_ir.
Before this PR:
After this PR: