Support QDQ transformations with com.microsoft.Quantize/Dequantize ops#17127
Merged
Conversation
…nsformerTests.QDQPropagation_Forward/Backward
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
skottmckay
previously approved these changes
Aug 24, 2023
…er script to handle subgraphs.
edgchen1
reviewed
Aug 24, 2023
edgchen1
previously approved these changes
Aug 24, 2023
edgchen1
approved these changes
Aug 25, 2023
Member
Contributor
Author
@yufenglee The work is being broken down into separate/smaller PRs. This specific PR focuses on making sure contrib QDQ ops can be optimized in the same manner as ONNX ops (please refer to the PR description for details). The next PR (linked in the description) adds int16 support, but I'd like to get this one merged in before starting reviews on it. |
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
microsoft#17127) ### Description - Enables int32 support for com.microsoft.DequantizeLinear (contrib op) - Makes the `zero_point` input optional for Quantize/Dequantize contrib ops - Enables QDQ transformations with the Quantize/Dequantize contrib ops - Update tests: EnsureUniqueDQForNodeUnitTests, QDQTransformerTests, TransposeOptimizerTests ### Testing List of tested graph transformations: - [x] QDQSelectorActionTransformer - qdq_transformer_test.cc - [x] QDQS8ToU8Transformer - qdq_transformer_test.cc - [x] DoubleQDQPairsRemover - qdq_transformer_test.cc - [x] IdenticalChildrenConsolidation - qdq_transformer_test.cc - [x] QDQPropagation - qdq_transformer_test.cc - [x] QDQFinalCleanup - qdq_transformer_test.cc - [x] CliQuantFusion - qdq_transformer_test.cc - [x] ReluQuantFusion - qdq_transformer_test.cc - [x] EnsureUniqueDQForNodeUnit - ensure_unique_dq_for_node_unit_test.cc - [x] TransposeOptimizer - transpose_optimizer_test.cc - [x] CommonSubexpressionElimination - graph_transform_test.cc - [x] ConstantFolding - graph_transform_test.cc ### Motivation and Context We need to [support mixed 16-bit/8-bit precision QDQ models](microsoft#17015). This PR is the first step in achieving this goal: we need to make QDQ contrib ops work with our optimizations/transformations. --------- Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Scott McKay <skottmckay@gmail.com>
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
7 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
zero_pointinput optional for Quantize/Dequantize contrib opsTesting
List of tested graph transformations:
Motivation and Context
We need to support mixed 16-bit/8-bit precision QDQ models. This PR is the first step in achieving this goal: we need to make QDQ contrib ops work with our optimizations/transformations.