pythonfix
nncf 2.13.0
Neural Networks Compression Framework
Neural Networks Compression Framework
Stars: 922, Watchers: 922, Forks: 229, Open Issues: 68The openvinotoolkit/nncf repo was created 4 years ago and the last code push was 3 days ago.
The project is popular with 922 github stars!
How to Install nncf
You can install nncf using pip
pip install nncf
or add it to a project with poetry
poetry add nncf
Package Details
- Author
- Intel
- License
- Apache-2.0
- Homepage
- https://github.com/openvinotoolkit/nncf
- PyPi:
- https://pypi.org/project/nncf/
- GitHub Repo:
- https://github.com/openvinotoolkit/nncf
Classifiers
Related Packages
Errors
A list of common nncf errors.
Code Examples
Here are some nncf code examples and snippets.
GitHub Issues
The nncf package has 68 open issues on GitHub
- Remove xception from ptq tests
- Speedup of PTQ
- Add LINEAR_ACTIVATIONS_UNSQUEEZE_BN_SQUEEZE fused pattern
- NNCF v2.5 increases tensor size and model size raising NPU errors
- New test_quantize_conformance for HF
- Add parameters
strict_check_scopes - Move the FC_BN_HSWISH_ACTIVATION pattern from fused to ignored
- [ONNX] Add support of correct quantization of MatMul
- [OV][POT] Disable MMAP
- [PTQ][OV] Remove inplace = False workaround for previous OpenVino release
- [PTQ][OV] SmoothQuant algorithm
- Move some HWFusedPatterns to IgnoredPatterns
- Update examples, tests, readme metrics
- ModuleNotFoundError: No module named 'jstyleson' when import nncf
- [PTQ][OV][ONNX] BiasCorrection update
Related Packages & Articles
transformers 4.45.2
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
beir 2.0.0
A Heterogeneous Benchmark for Information Retrieval
farm-haystack 1.26.3
LLM framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data.
onnx 1.17.0
Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. Currently we focus on the capabilities needed for inferencing (scoring).
datasets 3.0.1
HuggingFace community-driven open-source library of datasets
adapter-transformers 4.0.0
Deprecated adapter-transformers package. Use adapters package instead.
thinc 9.1.1
A refreshing functional take on deep learning, compatible with your favorite libraries
nlp 0.4.0
HuggingFace/NLP is an open library of NLP datasets.
autogluon 1.1.1
Fast and Accurate ML in 3 Lines of Code