faiss-cpu1.8.0.post1
Published
A library for efficient similarity search and clustering of dense vectors.
pip install faiss-cpu
Package Downloads
Authors
Project URLs
Requires Python
>=3.8
Dependencies
faiss-wheels
faiss python wheel packages.
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 ofgeneric
,avx2
,avx512
. Note that AVX option is only available in x86_64 arch.FAISS_ENABLE_GPU
: Setting this variable toON
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
.