Enable ClipQuantFusion exclusively on CPU EP #20627
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
yihonglyu
changed the title
yihonglyu
changed the title
yihonglyu
requested review from
adrianlizarraga,
yufenglee,
skottmckay and
jywu-msft
yufenglee
approved these changes
May 10, 2024
edgchen1
reviewed
May 10, 2024
poweiw
pushed a commit
to poweiw/onnxruntime
that referenced
this pull request
Jun 25, 2024
### Motivation and Context The Intel NPU does not support 16-bit int quantized operators. Consequently, the execution provider removes the QuantizeLinear/DeQuantizeLinear (Q/DQ) operators from node units and executes the operation as FP16 in the backend. However, if a Clip operator was fused into a Q operator in the node unit, the removal of Q/DQ operators results in inaccuracies because the effect of the original Clip operators is lost. Consider the following example: - FP32 model: -> Op_FP32 -> Clip -> - QDQ model: -> (DQ-> Op_FP32 -> Q) -> (DQ' -> Clip -> Q') -> - After ClipQuantFusion: -> (DQ-> Op_FP32 -> Q) -> (DQ' -> Q') -> - Intel Execution Provider strips Q/DQ: -> Op_FP16 -> To solve this issue, we have enabled ClipQuantFusion exclusively on the CPU execution provider.
adrianlizarraga
added a commit
that referenced
this pull request
Jul 19, 2024
### Description Moves the `Relu -> QuantizeLinear` fusion to Level2 optimizations for CPU EP only. ### Motivation and Context See the related PR for motivation and context: #20627
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Outdated suggestions cannot be applied.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.
Motivation and Context
The Intel NPU does not support 16-bit int quantized operators. Consequently, the execution provider removes the QuantizeLinear/DeQuantizeLinear (Q/DQ) operators from node units and executes the operation as FP16 in the backend. However, if a Clip operator was fused into a Q operator in the node unit, the removal of Q/DQ operators results in inaccuracies because the effect of the original Clip operators is lost.
Consider the following example:
To solve this issue, we have enabled ClipQuantFusion exclusively on the CPU execution provider.