resolve args datatype mismatch for split LPT #33160
Open
+6
−0
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
github-actions
bot
added
the
category: LP transformations
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Outdated suggestions cannot be applied.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.
We are enabling CoPilot models on OV GPU. The models are quantized in uint8/int8 or uint16/int16 datatypes.
FQ layers with int16/uint16 data types are stripped.
https://github.com/openvinotoolkit/openvino/blob/master/src/common/low_precision_transformations/src/qdq_stripping.cpp
With one model, we observer the below error which happens at split LPT transformation.
One input (Gather output) is in FP32 since DQ layers after Gather are stripped and the other input is in FP16 which cause mismatch between input data types during multiplication.
https://github.com/openvinotoolkit/openvino/blob/master/src/common/low_precision_transformations/src/split.cpp
To resolve that issue, conversion between data types happen before elementwise (mult) operation.
Tickets: