Add onnx.Abs to tosa.Abs lowering with quant types#605
Draft
tr00 wants to merge 1 commit into
Draft
Conversation
jorickert
reviewed
Mar 10, 2026
| type); | ||
| } | ||
|
|
||
| inline bool isTOSAQuantizedInt(mlir::Type type) { |
There was a problem hiding this comment.
Could you please move the implementation to the .cpp file?
For a small function like this it does not make a big difference, but generally having implementations in .cpp files helps to keep compile time and recompilations down
| type); | ||
| } | ||
|
|
||
| inline bool isTOSAQuantizedInt(mlir::Type type) { |
There was a problem hiding this comment.
Suggested change
| inline bool isTOSAQuantizedInt(mlir::Type type) { | |
| inline bool isTOSAUniformQuantizedInt(mlir::Type type) { |
| } | ||
|
|
||
| func.func @test_abs_qi8(%arg0: tensor<3x!quant.uniform<i8:f32, 1.0>>) -> tensor<3x!quant.uniform<i8:f32, 1.0>> { | ||
| %0 = "onnx.Abs"(%arg0) : (tensor<3x!quant.uniform<i8:f32, 1.0>>) -> tensor<3x!quant.uniform<i8:f32, 1.0>> |
There was a problem hiding this comment.
Could we get a test where the input and output quantization parameters are not the same?
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Changed that ONNX-to-TOSA conversion now allows for per-tensor quantized types from the quant dialect.
Provided test that shows onnx.Abs to tosa.Abs lowering with quant types.