Neural Network Compression Framework (NNCF)

Neural Network Compression Framework (NNCF) provides a suite of post-training and training-time algorithms for optimizing inference of neural networks in OpenVINO™ with a minimal accuracy drop.

NNCF is designed to work with models from PyTorch, TorchFX, TensorFlow, ONNX and OpenVINO™.

NNCF provides samples that demonstrate the usage of compression algorithms for different use cases and models. See compression results achievable with the NNCF-powered samples on the NNCF Model Zoo page.

The framework is organized as a Python* package that can be built and used in a standalone mode. The framework architecture is unified to make it easy to add different compression algorithms for both PyTorch and TensorFlow deep learning frameworks.

For more information about NNCF, see:

• NNCF repository
• User documentation
• NNCF API documentation
• Usage examples
• Notebook tutorials
• NNCF Compressed Model Zoo

Table of contents

• Key Features
• Installation
• Third-party integration

Key Features

Post-Training Compression Algorithms

Compression algorithm	OpenVINO	PyTorch	TorchFX	TensorFlow	ONNX
Post-Training Quantization	Supported	Supported	Experimental	Supported	Supported
Weights Compression	Supported	Supported	Experimental	Not supported	Not supported
Activation Sparsity	Not supported	Experimental	Not supported	Not supported	Not supported

Training-Time Compression Algorithms

Compression algorithm	PyTorch	TensorFlow
Quantization Aware Training	Supported	Supported
Weight-Only Quantization Aware Training with LoRA and NLS	Supported	Not Supported
Mixed-Precision Quantization	Supported	Not supported
Sparsity	Supported	Supported
Filter pruning	Supported	Supported
Movement pruning	Experimental	Not supported

• Automatic, configurable model graph transformation to obtain the compressed model.

  NOTE: Limited support for TensorFlow models. Only models created using Sequential or Keras Functional API are supported.

• Common interface for compression methods.
• GPU-accelerated layers for faster compressed model fine-tuning.
• Distributed training support.
• Git patch for prominent third-party repository (huggingface-transformers) demonstrating the process of integrating NNCF into custom training pipelines.
• Exporting PyTorch compressed models to ONNX* checkpoints and TensorFlow compressed models to SavedModel or Frozen Graph format, ready to use with OpenVINO™ toolkit.
• Support for Accuracy-Aware model training pipelines via the Adaptive Compression Level Training and Early Exit Training.

Installation Guide

For detailed installation instructions, refer to the Installation guide.

NNCF can be installed as a regular PyPI package via pip:

pip install nncf

NNCF is also available via conda:

conda install -c conda-forge nncf

System requirements of NNCF correspond to the used backend. System requirements for each backend and the matrix of corresponding versions can be found in installation.md.

Third-party Repository Integration

NNCF may be easily integrated into training/evaluation pipelines of third-party repositories.

Used by

• HuggingFace Optimum Intel

  NNCF is used as a compression backend within the renowned transformers repository in HuggingFace Optimum Intel. For instance, the command below exports the Llama-3.2-3B-Instruct model to OpenVINO format with INT4-quantized weights:

  optimum-cli export openvino -m meta-llama/Llama-3.2-3B-Instruct --weight-format int4 ./Llama-3.2-3B-Instruct-int4
  

• Ultralytics

  NNCF is integrated into the Intel OpenVINO export pipeline, enabling quantization for the exported models.

• ExecuTorch

  NNCF is used as primary quantization framework for the ExecuTorch OpenVINO integration.

• torch.compile

  NNCF is used as primary quantization framework for the torch.compile OpenVINO integration.

• OpenVINO Training Extensions

  NNCF is integrated into OpenVINO Training Extensions as a model optimization backend. You can train, optimize, and export new models based on available model templates as well as run the exported models with OpenVINO.

NNCF Compressed Model Zoo

List of models and compression results for them can be found at our NNCF Model Zoo page.

Citing

@article{kozlov2020neural,
    title =   {Neural network compression framework for fast model inference},
    author =  {Kozlov, Alexander and Lazarevich, Ivan and Shamporov, Vasily and Lyalyushkin, Nikolay and Gorbachev, Yury},
    journal = {arXiv preprint arXiv:2002.08679},
    year =    {2020}
}

Telemetry

NNCF as part of the OpenVINO™ toolkit collects anonymous usage data for the purpose of improving OpenVINO™ tools. You can opt-out at any time by running the following command in the Python environment where you have NNCF installed:

opt_in_out --opt_out

More information available on OpenVINO telemetry.