{"id":13935724,"url":"https://github.com/kyamagu/faiss-wheels","last_synced_at":"2025-07-19T21:30:32.336Z","repository":{"id":40680547,"uuid":"194008918","full_name":"kyamagu/faiss-wheels","owner":"kyamagu","description":"Community-maintained faiss wheel builder","archived":false,"fork":false,"pushed_at":"2025-07-15T02:22:00.000Z","size":207,"stargazers_count":341,"open_issues_count":6,"forks_count":40,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-07-15T04:41:01.724Z","etag":null,"topics":["nearest-neighbor-search","python"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/faiss-cpu/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kyamagu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2019-06-27T02:29:15.000Z","updated_at":"2025-07-14T00:18:55.000Z","dependencies_parsed_at":"2023-12-21T04:22:45.818Z","dependency_job_id":"822524d6-17ce-49bc-b23f-4be4e9babe87","html_url":"https://github.com/kyamagu/faiss-wheels","commit_stats":{"total_commits":327,"total_committers":2,"mean_commits":163.5,"dds":0.09174311926605505,"last_synced_commit":"bf4fd5383db00ef8e09d02a438a7b2b4f8c11763"},"previous_names":[],"tags_count":24,"template":false,"template_full_name":null,"purl":"pkg:github/kyamagu/faiss-wheels","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyamagu%2Ffaiss-wheels","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyamagu%2Ffaiss-wheels/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyamagu%2Ffaiss-wheels/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyamagu%2Ffaiss-wheels/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kyamagu","download_url":"https://codeload.github.com/kyamagu/faiss-wheels/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyamagu%2Ffaiss-wheels/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265425734,"owners_count":23762903,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["nearest-neighbor-search","python"],"created_at":"2024-08-07T23:02:02.094Z","updated_at":"2025-07-19T21:30:32.323Z","avatar_url":"https://github.com/kyamagu.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# faiss-wheels\n\n[![Build](https://github.com/kyamagu/faiss-wheels/actions/workflows/build.yml/badge.svg)](https://github.com/kyamagu/faiss-wheels/actions/workflows/build.yml)\n[![PyPI](https://img.shields.io/pypi/v/faiss-cpu?label=faiss-cpu)](https://pypi.org/project/faiss-cpu/)\n\nfaiss python wheel packages.\n\n- [faiss](https://github.com/facebookresearch/faiss)\n\n## Overview\n\nThis repository provides scripts to build wheel packages for the\n[faiss](https://github.com/facebookresearch/faiss) library.\n\n- Builds CPU-only version with [cibuildwheel](https://github.com/pypa/cibuildwheel/).\n- Bundles OpenBLAS in Linux/Windows\n- Uses Accelerate framework in macOS\n\nThere is also a source package to customize the build process.\n\n\u003e **Note**\n\u003e GPU binary package is discontinued as of 1.7.3 release. Build a source package to support GPU features.\n\n### Install\n\nInstall the CPU-only binary package by:\n\n```bash\npip install faiss-cpu\n```\n\nNote that the package name is `faiss-cpu`.\n\n## Supporting GPU or customized build configuration\n\nThe PyPI binary package does not support GPU.\nTo support GPU methods or use faiss with different build configuration, build a source package.\nFor building the source package, swig 3.0.12 or later needs to be available.\nAlso, there should be all the required prerequisites for building faiss itself, such as `nvcc` and CUDA toolkit.\n\n## Building faiss\n\n*The source package assumes faiss and OpenBLAS are already built and installed in the system.*\nIf not done so elsewhere, build and install the faiss library first.\nThe following example builds and installs faiss with GPU support and avx512 instruction set.\n\n```bash\ngit clone https://github.com/facebookresearch/faiss.git\ncd faiss\ncmake . -B build -DFAISS_ENABLE_GPU=ON -DFAISS_ENABLE_PYTHON=OFF -DFAISS_OPT_LEVEL=avx512\ncmake --build build --config Release -j\ncmake --install build install\ncd ..\n```\n\nSee the official\n[faiss installation instruction](https://github.com/facebookresearch/faiss/blob/master/INSTALL.md)\nfor more on how to build and install faiss.\n\n### Building and installing a source package\n\nOnce faiss is built and installed, build the source package.\nThe following builds and installs the faiss-cpu source package with GPU and AVX512.\n\n```bash\nexport FAISS_ENABLE_GPU=ON FAISS_OPT_LEVEL=avx512\npip install --no-binary :all: faiss-cpu\n```\n\nThere are a few environment variables that specifies build-time options.\n- `FAISS_INSTALL_PREFIX`: Specifies the install location of faiss library, default to `/usr/local`.\n- `FAISS_OPT_LEVEL`: Faiss SIMD optimization, one of `generic`, `avx2`, `avx512`. Note that AVX option is only available in x86_64 arch.\n- `FAISS_ENABLE_GPU`: Setting this variable to `ON` builds GPU wrappers. Set this variable if faiss is built with GPU support.\n- `CUDA_HOME`: Specifies CUDA install location for building GPU wrappers, default to `/usr/local/cuda`.\n\nNote that you can build a custom wheel package without installing it. The resulting package can be installed in the other python environment as long as the ABI is the same. Otherwise, use [`auditwheel`](https://github.com/pypa/auditwheel) or similar tools to package the binary dependency after building a wheel.\n\n```bash\nexport FAISS_ENABLE_GPU=ON FAISS_OPT_LEVEL=avx512\npip wheel --no-binary :all: faiss-cpu\n```\n\n\u003e **Note**\n\u003e Currently, the source package only supports the OpenBLAS backend; other BLAS implementation is not supported.\n\n## Development\n\nThis repository is intended to support PyPI distribution for the official [faiss](https://github.com/facebookresearch/faiss) library.\nThe repository contains the CI workflow based on [cibuildwheel](https://github.com/pypa/cibuildwheel/).\nFeel free to make a pull request to fix packaging problems.\n\nOther relevant resources:\n\n- [Packaging projects with GPU code](https://pypackaging-native.github.io/key-issues/gpus/)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkyamagu%2Ffaiss-wheels","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkyamagu%2Ffaiss-wheels","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkyamagu%2Ffaiss-wheels/lists"}