[QNN EP] Support Conv + Clip/Relu fusion #21537
Merged
Conversation
This file contains 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
adrianlizarraga
commented
Jul 29, 2024
adrianlizarraga
commented
Jul 29, 2024
onnxruntime/core/providers/qnn/builder/qnn_node_group/hardsigmoid_mul_fusion.cc
Show resolved
Hide resolved
HectorSVC
reviewed
Jul 29, 2024
jywu-msft
approved these changes
Aug 2, 2024
HectorSVC
approved these changes
Aug 2, 2024
|
Hi @MaanavD, @sophies927, and @prathikr. We would also like to cherry-pick this PR. We can provide more context. |
prathikr
pushed a commit
that referenced
this pull request
Aug 2, 2024
### Description - Supports quantized Conv + Activation on the HTP backend: - Translates `DQs -> Conv -> Relu/Clip -> Q` into a single QNN Conv operator if the Relu (or Clip) are redundant. ### Motivation and Context Expands support for QDQ models created with tools that do not wrap Relu or Clip with QDQ nodes. This PR introduces the `IQnnNodeGroup` class. In the same way that a `NodeUnit` represents a collection of `Nodes`, a `IQnnNodeGroup` can represent one or more `NodeUnits` that are translated into a QNN operator. QNN EP parses the ONNX graph to create a list of `IQnnNodeGroup` objects, each representing a single `NodeUnit` or a fusion of multiple `NodeUnits`.
prathikr
pushed a commit
that referenced
this pull request
Aug 3, 2024
### Description - Supports quantized Conv + Activation on the HTP backend: - Translates `DQs -> Conv -> Relu/Clip -> Q` into a single QNN Conv operator if the Relu (or Clip) are redundant. ### Motivation and Context Expands support for QDQ models created with tools that do not wrap Relu or Clip with QDQ nodes. This PR introduces the `IQnnNodeGroup` class. In the same way that a `NodeUnit` represents a collection of `Nodes`, a `IQnnNodeGroup` can represent one or more `NodeUnits` that are translated into a QNN operator. QNN EP parses the ONNX graph to create a list of `IQnnNodeGroup` objects, each representing a single `NodeUnit` or a fusion of multiple `NodeUnits`.
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.
Description
DQs -> Conv -> Relu/Clip -> Qinto a single QNN Conv operator if the Relu (or Clip) are redundant.Motivation and Context
Expands support for QDQ models created with tools that do not wrap Relu or Clip with QDQ nodes.
This PR introduces the
IQnnNodeGroupclass. In the same way that aNodeUnitrepresents a collection ofNodes, aIQnnNodeGroupcan represent one or moreNodeUnitsthat are translated into a QNN operator. QNN EP parses the ONNX graph to create a list ofIQnnNodeGroupobjects, each representing a singleNodeUnitor a fusion of multipleNodeUnits.