faiss-wheels

faiss python wheel packages.

faiss

Overview

This repository provides scripts to build wheel packages for the faiss library.

Builds CPU-only version with cibuildwheel.
Bundles OpenBLAS in Linux/Windows
Uses Accelerate framework in macOS

There is also a source package to customize the build process.

Note GPU package has been supported until version 1.7.2, but is not available since version 1.7.3 due to the PyPI limitation.

Install

Install a binary package by:

pip install faiss-cpu

Building source package

If there is a custom built faiss library in the system, build source package for the best performance.

Prerequisite

The source package assumes faiss is already built and installed in the system. Build and install the faiss library first.

cd faiss
cmake . -B build -DFAISS_ENABLE_GPU=OFF -DFAISS_ENABLE_PYTHON=OFF -DFAISS_OPT_LEVEL=avx512
cmake --build build --config Release -j
cmake --install build install
cd ..

See the official faiss installation instruction for more on how to build and install faiss.

For building sdist, swig 3.0.12 or later needs to be available.

Building a source distribution

The following builds and installs the faiss-cpu source package with AVX512.

export FAISS_OPT_LEVEL=avx512
pip install --no-binary :all: faiss-cpu

The following example builds a GPU wheel.

export FAISS_ENABLE_GPU=ON
pip install --no-binary :all: faiss-cpu

There are a few environment variables that specifies build-time options.

FAISS_INSTALL_PREFIX: Specifies the install location of faiss library, default to /usr/local.
FAISS_OPT_LEVEL: Faiss SIMD optimization, one of generic, avx2, avx512. Note that AVX option is only available in x86_64 arch.
FAISS_ENABLE_GPU: Setting this variable to ON builds GPU wrappers. Set this variable if faiss is built with GPU support.
CUDA_HOME: Specifies CUDA install location for building GPU wrappers, default to /usr/local/cuda.

kyamagu / faiss-wheels