[CPU EP] Add blocked quantization to DequantizeLinear op kernel #20901
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
fajin-corp
commented
Jun 3, 2024
fajin-corp
commented
Jun 4, 2024
yufenglee
reviewed
Jun 4, 2024
yufenglee
reviewed
Jun 4, 2024
yufenglee
reviewed
Jun 4, 2024
yufenglee
reviewed
Jun 4, 2024
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Outdated suggestions cannot be applied.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.
Description
Added blocked quantization to DequantizeLinear op kernel. All existing input types and output types are supported. All axes are supported.
The implementation in the PR is naive - single thread and scalar instructions. Multi-threading and vector instructions are planned in the future based on the needs.
Motivation and Context
onnx introduced blocked quantization in opset 21 for DequantizeLinear. This PR adds the spec support in onnx runtime.