[bugfix] don't allow qlinearmatmul to match output Q/DQ block meant for next quantizable node #1700
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Outdated suggestions cannot be applied.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.
currently, if a Q/DQ -> MatMul -> Q/DQ -> MatMul series of nodes occurs, the first matmul may be matched as a target for a
QLinearMatMul
conversion even though the output Q/DQ block is meant for the second matmulthis adds a simple check to skip these cases. this issue was brought up in testing of quantizing distilbert by @rahul-tuli
test-plan:
to be tested by @rahul-tuli