{"full_name":"facebookresearch/faiss","owner":"facebookresearch","name":"faiss","shard":"1","url":"https://github.com/facebookresearch/faiss","description":"A library for efficient similarity search and clustering of dense vectors.","homepage":"https://faiss.ai","topics":[],"tag_pages":[],"language":"C++","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/16943930?v=4","created_at":"2017-02-07T16:07:05Z","pushed_at":"2026-11-14T16:33:00Z","metrics":{"stars":41706,"forks":4643,"watchers":496,"issues":2835,"prs":2774,"releases":30,"issues_open":242,"issues_closed":2593,"prs_open":149,"prs_closed":2487,"prs_merged":138,"discussions":277},"growth":{"day":{"stars":46,"forks":6,"base_day":"2026-11-15"},"week":{"stars":437,"forks":55,"base_day":"2026-11-09"},"month":{"stars":583,"forks":92,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-06","2026-09-07","2026-09-08","2026-09-09","2026-09-10","2026-09-11","2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[40789,40801,40802,40809,40812,40813,40813,40820,40842,40850,40852,40853,40856,40872,40878,40888,40890,40891,40893,40906,40911,40917,40926,40931,40937,40950,40957,40964,40972,40980,40986,40995,40997,41011,41015,41028,41087,41099,41107,41113,41118,41123,41134,41144,41153,41162,41165,41167,41176,41185,41189,41197,41200,41216,41220,41223,41232,41236,41251,41255,41269,41303,41422,41492,41523,41611,41660,41706],"forks":[4500,4502,4503,4504,4505,4508,4508,4508,4510,4513,4513,4515,4514,4518,4517,4521,4522,4522,4523,4524,4525,4524,4526,4526,4526,4529,4529,4528,4530,4530,4532,4532,4534,4539,4539,4542,4550,4551,4551,4551,4552,4551,4550,4555,4556,4558,4558,4559,4562,4564,4566,4568,4570,4575,4575,4577,4578,4580,4584,4587,4588,4590,4606,4617,4623,4631,4637,4643],"watchers":[492,493,493,493,493,493,493,494,497,497,497,497,497,498,498,498,498,498,498,498,498,498,498,498,499,499,499,499,499,499,499,499,499,499,499,499,498,499,499,498,498,498,498,498,498,498,498,498,498,498,498,498,493,493,493,493,493,493,495,495,495,495,496,496,496,496,496,496],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,238,240,240,241,241,242],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,146,157,155,148,146,149]},"boards":{},"same_owner":[{"full_name":"facebookresearch/AugLy","name":"AugLy","shard":"1","boards":{}},{"full_name":"facebookresearch/ImageBind","name":"ImageBind","shard":"1","boards":{}},{"full_name":"facebookresearch/audiocraft","name":"audiocraft","shard":"1","boards":{}},{"full_name":"facebookresearch/codellama","name":"codellama","shard":"1","boards":{}},{"full_name":"facebookresearch/detectron2","name":"detectron2","shard":"1","boards":{}},{"full_name":"facebookresearch/detr","name":"detr","shard":"1","boards":{}},{"full_name":"facebookresearch/dinov2","name":"dinov2","shard":"1","boards":{}},{"full_name":"facebookresearch/dinov3","name":"dinov3","shard":"1","boards":{}},{"full_name":"facebookresearch/fastText","name":"fastText","shard":"1","boards":{}},{"full_name":"facebookresearch/hydra","name":"hydra","shard":"1","boards":{}},{"full_name":"facebookresearch/maskrcnn-benchmark","name":"maskrcnn-benchmark","shard":"1","boards":{}},{"full_name":"facebookresearch/mmf","name":"mmf","shard":"1","boards":{}},{"full_name":"facebookresearch/pifuhd","name":"pifuhd","shard":"1","boards":{}},{"full_name":"facebookresearch/pytorch3d","name":"pytorch3d","shard":"1","boards":{}},{"full_name":"facebookresearch/sam2","name":"sam2","shard":"1","boards":{}},{"full_name":"facebookresearch/sam3","name":"sam3","shard":"1","boards":{}},{"full_name":"facebookresearch/seamless_communication","name":"seamless_communication","shard":"1","boards":{}},{"full_name":"facebookresearch/segment-anything","name":"segment-anything","shard":"1","boards":{}},{"full_name":"facebookresearch/vggt","name":"vggt","shard":"1","boards":{}}],"issues":[{"number":105,"title":"Java interface of faiss","comments":26,"created_at":"2017-05-02T22:56:11Z"},{"number":2386,"title":"Faiss runs very slowly on M1 Mac","comments":18,"created_at":"2022-07-15T16:04:05Z"},{"number":4510,"title":"uv pip install support","comments":15,"created_at":"2025-08-06T09:39:59Z"},{"number":890,"title":"How It is Possible to Import and Use Faiss in Google Colab?","comments":13,"created_at":"2019-07-15T15:44:35Z"},{"number":2135,"title":"FAISS returns negative ids (not -1)","comments":13,"created_at":"2021-12-01T15:50:52Z"},{"number":3087,"title":"[Feature Request]Vector deduplication","comments":12,"created_at":"2023-10-10T18:21:19Z"},{"number":2868,"title":"Weird behaviour under macOS","comments":12,"created_at":"2023-05-19T17:14:52Z"},{"number":565,"title":"range_search on GPU","comments":12,"created_at":"2018-08-13T04:47:55Z"}],"discussions":[{"number":5672,"title":"SIMD Support for PPC64LE","comments":1,"category":"Q&A","created_at":"2026-09-25T20:35:53Z"},{"number":5537,"title":"HNSW distance compression vs. progressive graph search: matched-recall results on six 1M-scale datasets","comments":1,"category":"General","created_at":"2026-08-23T21:24:55Z"},{"number":5499,"title":"v1.15.0","comments":0,"category":"General","created_at":"2026-08-03T17:10:59Z"},{"number":5244,"title":"Clean-room Zig reimplementation reproduces published IVFPQ memory-compression numbers","comments":0,"category":"Show and tell","created_at":"2026-05-28T01:17:35Z"},{"number":5142,"title":"[Performance] Prefetch for on-disk inverted list","comments":3,"category":"Q&A","created_at":"2026-03-30T22:23:35Z"},{"number":4976,"title":"Need advice on weird memory usage pattern while building IndexIVFPQ iteratively","comments":1,"category":"Q&A","created_at":"2026-03-24T15:49:23Z"},{"number":4929,"title":"Moving a basic CPU index to GPU (Google Colab T4) for faster search?","comments":1,"category":"Q&A","created_at":"2026-03-16T21:07:03Z"},{"number":4830,"title":"Question about RaBitQ and RaBitQfs","comments":1,"category":"Q&A","created_at":"2026-02-23T17:44:53Z"}],"latest_release":{"name":"v1.16.0","tag":"v1.16.0","published_at":"2026-11-10T16:03:21Z","body":"## [1.16.0] - 2026-11-09\r\n\r\nAdded\r\n- fc1095a9314f892938bf83f59e7ac966b5095def e-means: add benchmarks reproducing the paper (#5845)\r\n- 2079677d10e5f6cf0823acd5aea453389cc866a2 e-means: add max_points_per_centroid (#5855)\r\n- 8e5843c5ec8697957276401f1acba0ebec58a329 Add regression test for flat search in a nested OpenMP region (#5754)\r\n- b80093c5b290578ed7de1975583e295309b4de81 Add DINO resident and SSD streaming e-means demos (#5815)\r\n- 97fdfb09848869f0e4bf09537eb814c3bf86bf49 Add optional IVF assignment for centroid-sharded e-means (#5817)\r\n- f6a82dc2fa89ebb34ceb7cce8750f9305d2f17db Add centroid-sharded e-means training (#5823)\r\n- 0136502d7ae5319a72ad35f7eb62e4eb364d8b1b Add native INT8 CuTe assignment to e-means (#5816)\r\n- 15b14b2862c06eb779c6c3d8d669b5df4b6b33ea Add FP8 CuTe assignment to e-means (#5820)\r\n- 13a33bf7f5e27e1bf531e4a21ba47a306dc97d9f Add CuTe assignment backend to e-means (#5818)\r\n- 7a038e7eb2f8c4c76c19ead6ed9c5485f5030fc5 Add INT8 Triton assignment to e-means (#5821)\r\n- 87b533977b9b536c1cc0b96daa191778b3cedd58 Add FP8 Triton assignment to e-means (#5819)\r\n- c8ab4f51ac0703419d7cc6950117d286d37c37ff Add Triton assignment backend to e-means (#5822)\r\n- f61f80a2c4ea7420364bd8f9153c8171efb1e1e3 Add reduced-precision assignment to e-means (#5814)\r\n- 8ac2fdc014e4f19ba30f617c038fb2719c984031 Add distributed E-means training (#5813)\r\n- 3795ee68fbecc0fa4ad027748735eb7f513948ee Add reference e-means implementations (#5812)\r\n- 951067d91521af476ebf0b5c51b26fa4bc98ad80 Print native crash diagnostics in Linux CMake CI (#5828)\r\n- 7648f5ffea474bdbdabab3d5e1a2a528db12c601 InvertedListScanner::distances_to_codes, with a block kernel for 8-bit PQ (#5807)\r\n- a6505c5c5d76eaf86f9196669564ee766a9a1b69 Expose caller-owned Dataset APIs for CAGRA (#5739)\r\n- 4caf5040c34ee16e069b14c24d09631b21a63133 Add MetalIndexBinaryFlat with GPU Hamming search and exact top-k selection (#5759)\r\n- 71c7f482d2da0aa1fbed179485818184a5d7df42 Add remove_ids to IndexShards and IndexReplicas, and add_with_ids to IndexReplicas (#5773)\r\n- 6964ecd829582bfdc9872c0c93acc5bf78696a0f Make the multi-GPU Python helpers work on the Metal backend (#5747)\r\n- b156cced9160a6e68086f6828692ca69a6dd87f8 feat(rvv): add bit-exact RVV decode_vector for raw-codec quantizers (#5689)\r\n- 8ff93a84010dabb605dfcb1f30511e80336fc006 Serialization, clone and index_factory support for IndexPiPNN (#5758)\r\n- 840aa1f4aff4b824989cfeee9e74236ad9585f66 Add HNSW level-0 links from a sample to remove search sinks (#5705)\r\n- 89e5eb519570efbfc5432324735d978c932d4ae3 Add IndexPiPNN, a PiPNN graph index with beam search (#5734)\r\n- 3effdb20dc6bd0ebc38d0b1c46c366f3667751a2 PiPNN build assembly (#5729)\r\n- 07979b10e64d39a611196483f103b2d7b349b5f7 Randomized Ball Carving partition (#5714)\r\n- 7069478c3f027edc8ece507158409208b2652d90 Numeric kernels\r\n- 7a057952fdb93fec7865eb5459e3956cd9108b8b HashPrune reservoir and sketch kernel (#5708)\r\n- b0074a3fa426027d9ff8575b44386d5922859ac9 Add fp16 support to `SuperKMeans` (#5692)\r\n- e7c44eb000bebb16f84be38a115caa5d333a8229 Add AVX-512 fp16 conversion kernels (#5694)\r\n- ea29bac75d0039ad9f3aa0351ac5cac6aabdb0bb RaBitQ: add batch-four estimates and 9-bit SIMD scoring (#5647)\r\n- 76c0e01e0f4db5f943b44cf85530e68efe29f355 Add GPU-accelerated IVFPQ search to the Metal backend (#5449)\r\n- 0db2f3088643c2b2d0bc1c3afdba1dc0c40fee1a rabitq neon kernels (#5532)\r\n- 430a41ee4c52cd070470e180c6d0f57888588d6b Native fp16 k-means training for Faiss IVF (#5671)\r\n- 6c8378e4f1b8d7a3a7986c2ca216923221fe6954 Add RVV implementation for decode_bf16_simd (#5641)\r\n- e24a371a701ddcb7fe460d87fd9c8f400c440848 feat(rvv): add vector arithmetic kernels (#5655)\r\n- 94a4331fee6524272a108d8eb5c176133a29c6b2 Add reranked types to IndexSQFastScan and fix flat RaBitQ filtering (#5661)\r\n- dcf8ebb34623c1b3dde08e495ef974c92a179c4e Support IDSelector in flat fast-scan search (#5660)\r\n- 1768a5a8e988706fcce2306865f18fce5b151115 Add RVV SIMD specialization for product quantizer distance-table computation (#5543)\r\n- ","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}