[QNN EP] Support Softmax/LogSoftmax with any axis attribute#17877
Merged
adrianlizarraga merged 5 commits intomainfrom Oct 12, 2023
Merged
[QNN EP] Support Softmax/LogSoftmax with any axis attribute#17877adrianlizarraga merged 5 commits intomainfrom
adrianlizarraga merged 5 commits intomainfrom
Conversation
adrianlizarraga
commented
Oct 11, 2023
…s axis == rank - 1 for opset < 13
HectorSVC
reviewed
Oct 11, 2023
onnxruntime/core/providers/qnn/builder/opbuilder/softmax_op_builder.cc
Outdated
Show resolved
Hide resolved
adrianlizarraga
added a commit
that referenced
this pull request
Oct 13, 2023
### Description We need to ensure that tensors are first created and validated by their producers. If we don't, then builders that need to modify their outputs may not be able to do so if consumers are processed first (due to caching of tensors). For example, the Tanh builder may need to override its output quant param for 16-bit QDQ. I've encountered a scenario (while working on a partner model) where the override was not being correctly applied due to the graph traversal order. I tried to fix this bug in a previous [PR](#17877 (comment)), but my fix was incorrect.
jchen351
pushed a commit
that referenced
this pull request
Oct 18, 2023
### Description We need to ensure that tensors are first created and validated by their producers. If we don't, then builders that need to modify their outputs may not be able to do so if consumers are processed first (due to caching of tensors). For example, the Tanh builder may need to override its output quant param for 16-bit QDQ. I've encountered a scenario (while working on a partner model) where the override was not being correctly applied due to the graph traversal order. I tried to fix this bug in a previous [PR](#17877 (comment)), but my fix was incorrect.
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
…t#17877) ### Description The QNN HTP backend only supports Softmax/LogSoftmax operators with an axis attribute set to `input_rank - 1` (i.e., the last dimension). This PR adds support for any axis by wrapping the QNN operator in transposes. ### Motivation and Context Support more models.
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
…soft#17913) ### Description We need to ensure that tensors are first created and validated by their producers. If we don't, then builders that need to modify their outputs may not be able to do so if consumers are processed first (due to caching of tensors). For example, the Tanh builder may need to override its output quant param for 16-bit QDQ. I've encountered a scenario (while working on a partner model) where the override was not being correctly applied due to the graph traversal order. I tried to fix this bug in a previous [PR](microsoft#17877 (comment)), but my fix was incorrect.
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.
Description
The QNN HTP backend only supports Softmax/LogSoftmax operators with an axis attribute set to
input_rank - 1(i.e., the last dimension). This PR adds support for any axis by wrapping the QNN operator in transposes.Motivation and Context
Support more models.