Repository navigation
Fix MatMulNBits benchmark model IR compatibility - #33577
Open
Srijan Keshri (arcusbuilds) wants to merge 1 commit into
Open
Srijan Keshri (arcusbuilds) wants to merge 1 commit into
Srijan Keshri (arcusbuilds) wants to merge 1 commit into
Conversation
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
Contributor
There was a problem hiding this comment.
🟢 Approval recommended
The focused compatibility fix preserves the graph and opset, adds regression coverage, and has no identified blocking issues.
No open issues 🎉
What changed in this PR
This PR fixes #33576 by pinning the MatMulNBits benchmark model to IR8, avoiding the newer default IR that ORT 1.23.2 rejects.
Changes:
- Explicitly sets IR8 while preserving the existing opset17 import.
- Adds a regression test asserting the serialized IR version and validating the model with the ONNX checker.
| File | Description |
|---|---|
| onnxruntime/test/python/transformers/test_profile_matmul_nbits.py | Adds IR-version and model-validity regression coverage. |
| onnxruntime/test/python/transformers/profile_matmul_nbits.py | Pins the generated benchmark model to IR8. |
Review effort: Balanced
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Set the MatMulNBits profiling model to IR8, matching opset17, and add a regression test.
Validation: the test fails before the fix and passes afterward. The model loads with ONNX 1.19.1 and ORT 1.23.2. Ruff lint and format checks pass.
Motivation and Context
ONNX 1.19.1 defaults to IR12, which ORT 1.23.2 rejects. The benchmark does not need that newer IR.
Fixes #33576