[Release_v2150] Update ReleaseNotes.md #3214
Open
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
github-actions
bot
added
documentation
KodiaqQ
assigned alexsu52, ljaljushkin, l-bat, nikita-savelyevv, kshpv, daniil-lyakhov, andrey-churkin, andreyanufr, anzr299 and AlexanderDokuchaev
|
@alexsu52, @ljaljushkin, @l-bat, @nikita-savelyevv, @andreyanufr, @andrey-churkin, @daniil-lyakhov, @kshpv, @AlexanderDokuchaev, @anzr299 fill the document with your changes for the upcoming release, please. |
|
no changes from my side |
|
@andrey-churkin , please add the deprecation note about create_compressed_model() in TF among the description of the related changes and the reference to the example. |
|
@l-bat , please update the list of new/updated notebooks with NNCF support. Here is a draft list from my side (to be confirmed): |
MaximProshin
requested review from
MaximProshin,
alexsu52,
l-bat,
nikita-savelyevv,
kshpv,
AlexanderDokuchaev,
anzr299,
andrey-churkin,
andreyanufr and
daniil-lyakhov
and removed request for
a team
MaximProshin
assigned MaximProshin and unassigned nikita-savelyevv, kshpv, anzr299, AlexanderDokuchaev, daniil-lyakhov, andrey-churkin and andreyanufr
l-bat
approved these changes
Jan 28, 2025
Comment on lines
+16
to
+18
| - Significantly faster data-free weight compression for OpenVINO models: INT4 compression is now up to 10x faster, while INT8 compression is up to 3x faster. The larger the model the higher the time reduction. | ||
| - AWQ weight compression is now up to 2x faster, improving overall runtime efficiency. | ||
| - Peak memory usage during INT4 data-free weight compression in the OpenVINO backend is reduced up to 50% for certain models. |
nikita-savelyevv
approved these changes
Jan 30, 2025
|
no changes from my side |
andreyanufr
approved these changes
Jan 31, 2025
AlexanderDokuchaev
approved these changes
Jan 31, 2025
kshpv
approved these changes
Jan 31, 2025
| - General: | ||
| - ... | ||
| - Features: | ||
| - (TorchFX, Experimental) Preview support for the new `quantize_pt2e` API has been introduced, enabling quantization of `torch.fx.GraphModule` models with the `OpenVINOQuantizer` and the `X86InductorQuantizer` quantizers. `quantize_pt2e` API utilizes `MinMax` algorithm statistic collectors, as well as `SmoothQuant`, `BiasCorrection` and `FastBiasCorrection` Post-Training Quantization algorithms. |
daniil-lyakhov
approved these changes
Jan 31, 2025
| - ... | ||
| - Features: | ||
| - (TorchFX, Experimental) Preview support for the new `quantize_pt2e` API has been introduced, enabling quantization of `torch.fx.GraphModule` models with the `OpenVINOQuantizer` and the `X86InductorQuantizer` quantizers. `quantize_pt2e` API utilizes `MinMax` algorithm statistic collectors, as well as `SmoothQuant`, `BiasCorrection` and `FastBiasCorrection` Post-Training Quantization algorithms. | ||
| - (TensorFlow) The `nncf.quantize()` method is now the recommended way for the quantization initialization for Quantization-Aware Training. Please refer to an [example](examples/quantization_aware_training/tensorflow/mobilenet_v2) for more details about how to use new approach. |
| - AWQ weight compression is now up to 2x faster, improving overall runtime efficiency. | ||
| - Peak memory usage during INT4 data-free weight compression in the OpenVINO backend is reduced up to 50% for certain models. | ||
| - Deprecations/Removals: | ||
| - (TensorFlow) The `nncf.tensorflow.create_compressed_model()` method is now marked as deprecated. Please use the `nncf.quantize()` method for the quantization initialization. |
| - Features: | ||
| - (TorchFX, Experimental) Preview support for the new `quantize_pt2e` API has been introduced, enabling quantization of `torch.fx.GraphModule` models with the `OpenVINOQuantizer` and the `X86InductorQuantizer` quantizers. `quantize_pt2e` API utilizes `MinMax` algorithm statistic collectors, as well as `SmoothQuant`, `BiasCorrection` and `FastBiasCorrection` Post-Training Quantization algorithms. | ||
| - (TensorFlow) The `nncf.quantize()` method is now the recommended way for the quantization initialization for Quantization-Aware Training. Please refer to an [example](examples/quantization_aware_training/tensorflow/mobilenet_v2) for more details about how to use new approach. | ||
| - (TensorFlow) Compression layers placement in the model now can be serialized and restored with new API functions: `nncf.tensorflow.get_config()` and `nncf.tensorflow.load_from_config()`. Please see [documentation](/docs/usage/training_time_compression/quantization_aware_training/Usage.md#saving-and-loading-compressed-models) for the saving/loading of a quantized model for more details. |
andrey-churkin
approved these changes
Jan 31, 2025
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.
Changes
Reason for changes
Related tickets
For the contributors:
Please add your changes (as the commit to the branch) to the list according to the template and previous notes;
Do not add tests-related notes;
Provide the list of the PRs (for all your notes) in the comment for the discussion;