Skip to content

Latest commit

 

History

History
150 lines (118 loc) · 7.21 KB

installation_guide.md

File metadata and controls

150 lines (118 loc) · 7.21 KB

Installation

  1. Installation

    1.1. Prerequisites

    1.2. Install from Binary

    1.3. Install from Source

    1.4. Install from AI Kit

  2. System Requirements

    2.1. Validated Hardware Environment

    2.2. Validated Software Environment

Installation

Prerequisites

You can install Neural Compressor using one of three options: Install single component from binary or source, or get the Intel-optimized framework together with the library by installing the Intel® oneAPI AI Analytics Toolkit.

The following prerequisites and requirements must be satisfied for a successful installation:

  • Python version: 3.8 or 3.9 or 3.10 or 3.11

Notes:

Install from Binary

  • Install from Pypi

    # install stable basic version from pypi
    pip install neural-compressor
    # [Experimental] install stable basic + PyTorch framework extension API from pypi 
    pip install neural-compressor[pt]
    # [Experimental] install stable basic + TensorFlow framework extension API from pypi 
    pip install neural-compressor[tf]
  • Install from test Pypi

    # install nightly version
    git clone https://github.com/intel/neural-compressor.git
    cd neural-compressor
    pip install -r requirements.txt
    # install nightly basic version from pypi
    pip install -i https://test.pypi.org/simple/ neural-compressor
  • Install from Conda

    # install on Linux OS
    conda install opencv-python-headless -c fastai
    conda install neural-compressor -c conda-forge -c intel
    # install on Windows OS
    conda install pycocotools -c esri
    conda install opencv-python-headless -c fastai
    conda install neural-compressor -c conda-forge -c intel

Install from Source

git clone https://github.com/intel/neural-compressor.git
cd neural-compressor
pip install -r requirements.txt
# build with basic functionality
python setup.py install

Install from AI Kit

The Intel® Neural Compressor library is released as part of the Intel® oneAPI AI Analytics Toolkit (AI Kit). The AI Kit provides a consolidated package of Intel's latest deep learning and machine optimizations all in one place for ease of development. Along with Neural Compressor, the AI Kit includes Intel-optimized versions of deep learning frameworks (such as TensorFlow and PyTorch) and high-performing Python libraries to streamline end-to-end data science and AI workflows on Intel architectures.

The AI Kit is distributed through many common channels, including from Intel's website, YUM, APT, Anaconda, and more. Select and download the AI Kit distribution package that's best suited for you and follow the Get Started Guide for post-installation instructions.

Download Guide
Download AI Kit AI Kit Get Started Guide

System Requirements

Validated Hardware Environment

Intel® Neural Compressor supports CPUs based on Intel 64 architecture or compatible processors:

  • Intel Xeon Scalable processor (formerly Skylake, Cascade Lake, Cooper Lake, Ice Lake, and Sapphire Rapids)
  • Intel Xeon CPU Max Series (formerly Sapphire Rapids HBM)

Intel® Neural Compressor supports GPUs built on Intel's Xe architecture:

  • Intel Data Center GPU Flex Series (formerly Arctic Sound-M)
  • Intel Data Center GPU Max Series (formerly Ponte Vecchio)

Intel® Neural Compressor quantized ONNX models support multiple hardware vendors through ONNX Runtime:

  • Intel CPU, AMD/ARM CPU, and NVidia GPU. Please refer to the validated model list.

Validated Software Environment

  • OS version: CentOS 8.4, Ubuntu 22.04, MacOS Ventura 13.5
  • Python version: 3.8, 3.9, 3.10, 3.11
Framework TensorFlow Intel
TensorFlow
Intel®
Extension for
TensorFlow*
PyTorch Intel®
Extension for
PyTorch*
ONNX
Runtime
MXNet
Version 2.15.0
2.14.1
2.13.0
2.14.0
2.13.0
2.12.0
2.14.0.1
2.13.0.0
1.2.0
2.1.0+cpu
2.0.1+cpu
1.13.1+cpu
2.1.0+cpu
2.0.1+cpu
1.13.1+cpu
1.16.3
1.15.1
1.14.1
1.9.1

Note: Set the environment variable TF_ENABLE_ONEDNN_OPTS=1 to enable oneDNN optimizations if you are using TensorFlow before v2.9. oneDNN is the default for TensorFlow since v2.9 (Intel Cascade Lake and newer CPUs).