[WC] Scale Estimation transpose_a support #3839
Open
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
NNCF PT
AlexanderDokuchaev
requested changes
Jan 15, 2026
| act_ch_axis = self._backend_entity.get_activation_channel_axis( | ||
| wp.node_with_weight, activation_port_id, act_shape | ||
| ) | ||
| act_ch_axis %= len(act_shape) |
Collaborator
There was a problem hiding this comment.
For which case it's need?
All tests still pass if remove the line.
|
|
||
| weight = self._backend_entity.get_weight(wp.node_with_weight, weight_port_id, model, graph) | ||
|
|
||
| activation_port_id = self._backend_entity.get_activation_port_id(wp.node_with_weight, graph) |
Collaborator
There was a problem hiding this comment.
This looks like copypast from awq.py.
Please think about to refactor it into a shared function.
Collaborator
Author
There was a problem hiding this comment.
WeightCompressionAlgoBackend.get_activation_channel_axis_and_shape is instroduced, please check
|
|
||
| matmul = opset.matmul(input_1, weight_data, transpose_a=False, transpose_b=False, name="MoE_MatMul") | ||
| if tranpsose_a: | ||
| transpose = opset.transpose(input_1, (0, 2, 1)) |
Collaborator
There was a problem hiding this comment.
Please check, looks like it never runs
Collaborator
Author
There was a problem hiding this comment.
Good catch,
It is, because of this skip https://github.com/daniil-lyakhov/nncf/blob/dl/sa_transpose_a/tests/openvino/native/quantization/test_weights_compression.py#L2369
I fixed the test and asked @anzr299 to remove the skip. Ticket 179366
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
Changes
transpose_aattribute for ONNX/OpenVINO backends in the Scale Estimation algorithmactivations_to_wc_statisticsmoved from the Scale Estimation algorithm to the GPTQReason for changes
Related tickets
173277
Tests
tests/cross_fw/test_templates/template_test_weights_compression.py::test_scale_estimation updated with the
transpose_acases