Aanuf/lut per layer merged #3684
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
the
documentation
2) Added extra advanced parameters for adapriva codebook.
github-actions
bot
added
the
NNCF OpenVINO
src/nncf/quantization/algorithms/weight_compression/algorithm.py
Outdated
Show resolved
Hide resolved
src/nncf/quantization/algorithms/weight_compression/codebook_estimation.py
Show resolved
Hide resolved
src/nncf/quantization/algorithms/weight_compression/codebook_estimation.py
Outdated
Show resolved
Hide resolved
src/nncf/quantization/algorithms/weight_compression/codebook_estimation.py
Outdated
Show resolved
Hide resolved
src/nncf/quantization/algorithms/weight_compression/codebook_estimation.py
Outdated
Show resolved
Hide resolved
| reduction_axes: tuple[int, ...], | ||
| config: WeightCompressionConfig, | ||
| wp: WeightCompressionParameters, | ||
| ) -> Tensor: |
src/nncf/quantization/algorithms/weight_compression/codebook_estimation.py
Outdated
Show resolved
Hide resolved
Comment on lines
+321
to
+329
| if self._num_elements == config.get_numpy_codebook().size: | ||
| variants[0] = fns.tensor( | ||
| config.get_numpy_codebook().data, backend=weight.backend, dtype=TensorDataType.float16 | ||
| ) | ||
| variants[1] = fns.tensor( | ||
| list(range(-self._num_elements // 2, self._num_elements - self._num_elements // 2)), | ||
| backend=weight.backend, | ||
| dtype=TensorDataType.float16, | ||
| ) |
Collaborator
There was a problem hiding this comment.
Could you please add comments to this part (in calculate_codebook fn as well) to expain the logic behind this?
src/nncf/quantization/algorithms/weight_compression/codebook_estimation.py
Outdated
Show resolved
Hide resolved
Comment on lines
2456
to
2458
| @pytest.mark.parametrize("value_type", [None, TensorDataType.float16, TensorDataType.f8e4m3, TensorDataType.int8]) | ||
| def test_adaptive_codebooks(value_type): | ||
| model = AWQMatmulModel().ov_model |
Collaborator
There was a problem hiding this comment.
Tests with reference codebooks and in per_group / not_per_group woudl be nice
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
Implemented computation of codebook based on k-means algorithm.
Reason for changes
Related tickets
CVS-169609
Tests