Skip to content

Latest commit

 

History

History
105 lines (84 loc) · 2.99 KB

installation.md

File metadata and controls

105 lines (84 loc) · 2.99 KB

Installation

  1. Install from Pypi

  2. Install from Source

    2.1. Prerequisites

    2.2. Install Intel Extension for Transformers

  3. System Requirements

    3.1. Validated Hardware Environment

    3.2. Validated Software Environment

Install from Pypi

Binary builds for python 3.8, 3.9 and 3.10 are available in Pypi

Note: Recommend install protobuf <= 3.20.0 if use onnxruntime <= 1.11

# install stable basic version from pypi
pip install intel-extension-for-transformers
# install stable basic version from conda
conda install -c intel intel_extension_for_transformers

Install from Source

Prerequisites

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

  • Python version: 3.8 or 3.9 or 3.10
  • GCC >= version 8 (on Linux)
    • version 11, if use the bf16-related features of the itrex backend
    • version 13, if use the fp16-related features of the itrex backend
  • Visual Studio (on Windows)

Install Intel Extension for Transformers

git clone https://github.com/intel/intel-extension-for-transformers.git itrex
cd itrex
pip install -r requirements.txt
# Install intel_extension_for_transformers
pip install -v .

System Requirements

Validated Hardware Environment

Intel® Extension for Transformers supports the following HWs:

  • Intel Xeon Scalable processor (Sapphire Rapids, Icelake, ...etc)
  • Intel Gaudi2
  • Intel Core Processors
  • Intel Xeon CPU Max Series

Validated Software Environment

  • OS version: CentOS 8.4, Ubuntu 20.04
  • Python version: 3.8, 3.9, 3.10
Framework Intel TensorFlow PyTorch IPEX
Version 2.13.0
2.12.0
2.1.0+cpu
2.0.0+cpu
2.1.0+cpu
2.0.0+cpu
  • OS version: Windows 10
  • Python version: 3.8, 3.9, 3.10
Framework Intel TensorFlow PyTorch
Version 2.13.0
2.0.0+cpu