Add declarative quantization optimization patterns. #97467
Merged
+59
−0
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
ccdc6ae to
cd21de8
Compare
This change introduces new declarative quantization patterns for TFLite in MLIR. The new patterns include: - Fusing a Dequantize op followed by a Quantize op into a single requantization op. - Fusing consecutive Quantize ops. - Removing no-op Quantize ops where the input and output types are the same. PiperOrigin-RevId: 787288671
cd21de8 to
3607270
Compare
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Outdated suggestions cannot be applied.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.
Add declarative quantization optimization patterns.
This change introduces new declarative quantization patterns for TFLite in MLIR.
The new patterns include: