SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
APACHE-2.0 License
Bot releases are hidden (Show)
Published by chensuyue 7 months ago
Improvement
Bug Fixes
Validated Configurations
Published by chensuyue 7 months ago
Highlights
Features
Improvement
Productivity
Bug Fixes
External Contributes
Validated Configurations
Published by chensuyue 10 months ago
Improvement
Bug Fixes
Examples
Validated Configurations
Published by chensuyue 10 months ago
Highlights
Features
Improvement
Productivity
Bug Fixes
Examples
Validated Configurations
Published by chensuyue 11 months ago
Features
Bug Fixes
Validated Configurations
Published by chensuyue about 1 year ago
Bug Fixes
Productivity
Validated Configurations
Published by chensuyue about 1 year ago
Highlights
Features
Improvement
Productivity
Bug Fixes
Examples
Validated Configurations
Published by chensuyue over 1 year ago
Highlights
Features
Improvement
Productivity
Bug Fixes
Examples
External Contributes
Validated Configurations
Published by chensuyue over 1 year ago
Bug Fixes
Examples
Validated Configurations
Published by chensuyue over 1 year ago
Highlights
Features
Improvement
Bug Fixes
Examples
Documentations
Validated Configurations
Published by kevinintel almost 2 years ago
Highlights
Features
Bug Fixes
Examples
Documentations
Validated Configurations
Published by kevinintel almost 2 years ago
Highlights
Features
Bug Fixes
Examples
Validated Configurations
Published by kevinintel about 2 years ago
Bug Fixes
Productivity
Examples
Validated Configurations
Published by kevinintel about 2 years ago
Highlights
We are excited to announce the release of Intel® Neural Compressor v1.14! We release new Pruning API for PyTorch, allowing users select better combinations of criteria, pattern and scheduler to achieve better pruning accuracy. This release also supports Keras input for TensorFlow quantization, and self-distilled quantization for better quantization accuracy.
New Features
Improvement
Bug Fixes
Productivity
Examples
Validated Configurations
Published by chensuyue about 2 years ago
Features
Support experimental auto-coding quantization for PyTorch
Refactor quantization utilities for ONNX Runtime
Bug fix
Validated Configurations
Published by ftian1 about 2 years ago
Features
Quantization
Mixed Precision
Neural Architecture Search
Sparsity
Strategy
Productivity
Ecosystem
Examples
Validated Configurations
Published by ftian1 over 2 years ago
Features
Quantization
Pruning
Sparsity
Productivity
Ecosystem
Examples
Validated Configurations
Published by ftian1 over 2 years ago
Features
Published by ftian1 over 2 years ago
Features
Productivity
Ecosystem
Examples
Validated Configurations
Channel | Links | Install Command | |
---|---|---|---|
Source | Github | https://github.com/intel/neural-compressor.git | $ git clone https://github.com/intel/neural-compressor.git |
Binary | Pip | https://pypi.org/project/neural-compressor | $ pip install neural-compressor |
Binary | Conda | https://anaconda.org/intel/neural-compressor | $ conda install neural-compressor -c conda-forge -c intel |
Please feel free to contact [email protected], if you get any questions.
Published by ftian1 almost 3 years ago
Features
Knowledge distillation
Quantization
Pruning
Reference bara-metal examples
Productivity
Ecosystem
Validated Configurations
Channel | Links | Install Command | |
---|---|---|---|
Source | Github | https://github.com/intel/neural-compressor.git | $ git clone https://github.com/intel/neural-compressor.git |
Binary | Pip | https://pypi.org/project/neural-compressor | $ pip install neural-compressor |
Binary | Conda | https://anaconda.org/intel/neural-compressor | $ conda install neural-compressor -c conda-forge -c intel |
Please feel free to contact [email protected], if you get any questions.