Fix DropQDQ not dropping Q/DQ around opset-22 MaxPool - #29201
Merged
Conversation
Contributor
Author
|
#27059 already proposes the same The thing this PR adds on top is updating Happy to close this in favor of #27059 if that one-line |
xadupre
approved these changes
Jun 22, 2026
Contributor
Author
|
@xadupre @tianleiwu |
tianleiwu
enabled auto-merge (squash)
June 23, 2026 07:05
tianleiwu
pushed a commit
that referenced
this pull request
Jun 23, 2026
### Description
ONNX added a `MaxPool-22` schema, but the DropQDQ selectors still
matched only `MaxPool-12`, so the `DequantizeLinear` / `QuantizeLinear`
around an opset-22 `MaxPool` were no longer dropped. This updates both
DropQDQ selector op-version maps to `{12, 22}`, matching the QDQ
propagation pass. (`MaxPool` stays pinned to integer-capable versions ≥
12.)
### Motivation and Context
Fixes #28770. Models that optimized to full integer at opset ≤ 21
regressed at opset 22+, blocking users from upgrading their opset.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
ONNX added a
MaxPool-22schema, but the DropQDQ selectors still matched onlyMaxPool-12, so theDequantizeLinear/QuantizeLineararound an opset-22MaxPoolwere no longer dropped. This updates both DropQDQ selector op-version maps to{12, 22}, matching the QDQ propagation pass. (MaxPoolstays pinned to integer-capable versions ≥ 12.)Motivation and Context
Fixes #28770. Models that optimized to full integer at opset ≤ 21 regressed at opset 22+, blocking users from upgrading their opset.