-
3.1. Prerequisites
For NeuralChat usage, please make sure if you have below system libraries installed:
apt-get update
apt-get install -y ffmpeg
apt-get install -y libgl1-mesa-glx libgl1-mesa-dev
apt-get install -y libsm6 libxext6
yum update -y
yum install -y mesa-libGL mesa-libGL-devel
yum install -y libXext libSM libXrender
For ffmpeg, please refer to how-to-install-ffmpeg-on-centos-rhel-8
Binary builds for python 3.9, 3.10 and 3.11 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
The following prerequisites and requirements must be satisfied for a successful installation:
- Python version: 3.9 or 3.10 or 3.11
- GCC >= version 10 (on Linux)
- Visual Studio (on Windows)
Note: If your system only have python3 or you meet error
python: command not found
, please runln -sf $(which python3) /usr/bin/python
.
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 .
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
- OS version: CentOS 8.4, Ubuntu 20.04
- Python version: 3.9, 3.10, 3.11
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: 3.9, 3.10, 3.11
Framework | Intel TensorFlow | PyTorch |
---|---|---|
Version | 2.13.0 | 2.1.0+cpu |