This is an automated email from the ASF dual-hosted git repository.
airborne pushed a change to branch faiss
in repository https://gitbox.apache.org/repos/asf/doris-thirdparty.git
discard 8bb97aa85c0 Fix CQS signal readability-braces-around-statements in
fbcode/faiss/perf_tests (#4458)
discard d7b000b89d5 Fix CQS signal readability-braces-around-statements in
fbcode/faiss/tests (#4457)
discard b4534d8b0dd `int8` support for cuVS cagra (#4439)
discard b9ee45d9575 Fix indexes after fp16 change (#4452)
discard d4a6a098bce Fix CQS signal readability-braces-around-statements in
fbcode/faiss (#4454)
discard 61d902ecc59 Fix CQS signal readability-braces-around-statements in
fbcode/faiss/gpu (#4453)
discard f78699b5188 BW compatibility for read & write with `numeric_type_` in
cagra (#4441)
discard 0451215bbb1 Fix CQS signal facebook-unused-include-check in
fbcode/faiss (#4451)
discard 424f248ed11 Upgrade cuVS version to 25.08 (#4394)
discard 9595cbb1ca2 Fix CQS signal readability-braces-around-statements in
fbcode/faiss/benchs (#4449)
discard 1ff5912ca00 Fix CQS signal readability-braces-around-statements in
fbcode/faiss/impl (#4447)
discard e6981c7b912 Revert D78330300 (#4448)
discard 7ba7d292448 Fix CQS signal readability-braces-around-statements in
fbcode/faiss/tutorial (#4446)
discard 7c2bdb89e80 Fix CQS signal facebook-unused-include-check in
fbcode/faiss/utils (#4435)
discard 6d9c3ce7714 Remove cuVS CUDA 11.8 CI (#4444)
discard 2954f1f5180 Fix CQS signal facebook-unused-include-check in
fbcode/faiss/perf_tests (#4443)
discard 71f775b7ea9 Add support for IndexIDMap with Cagra fp16 (#4411)
discard 004bee8fdc0 Fix CQS signal facebook-unused-include-check in
fbcode/faiss/impl (#4436)
discard 63d787ba860 Improve naming of the residual_quantizer_encode_steps.cpp
file (#4433)
discard cd3699ea739 Faiss + Cuvs Example Notebook (#4434)
discard c77c87a9b4f Common ancestor to top-k result handlers (#4414)
discard e45ae24a27d Add rabitq to reverse factory string so telemetry wrapper
will log it (#4428)
discard 4b33dea100e Remove Debug Statement (#4425)
discard bb58f6dbed8 Fix invalid long_description in setup.py (#4398)
discard 8a491e0377e Add option to link cuda statically (#4422)
discard 5af8f99bc79 remove ABS_INNER_PRODUCT metric (#4408)
discard a7044ee247e support extra metrics in IVF (#4409)
discard 11904f69817 Support decode_vectors (sa_decode but no decode_listnos)
in multiple IVF index (#4400)
discard ee9d18a27e6 Fix building on mingw (#4420)
discard 520c15da16e fix: add avx2 in python if avx512 enabled (#4419)
discard 646d45acc75 Add workaround to check SVE support when numpy.distutils
is not available (#4416)
discard 1deb5c60e0b Github actions: upgrade windows-2019 to windows-2022
(#4417)
discard 22d96426336 IndexFlat: Reconstruct validate if key < ntotal (#4415)
discard aad35f8bcac Dsweet/gowers distance (#4371)
discard dd0d40b57e6 Update the dependency for submitit in faiss_bench_fw
(#4410)
discard 3ad3eec575f cmake: disable installing external documents under
docs/faiss (#4406)
discard 539716ac9fe Increase top-k limit on GPU for cuVS (#4325)
discard b6e6ec61ad3 Pin openblas 0.3.30 to fix nightly breakage (#4404)
discard bf10844e9f4 generated METADATA.bzl (#4401)
discard 752b687150f cuVS Cagra FP16 support (#4384)
discard e10965a62b4 Add cuVS filter conversion utility (#4378)
discard 3f4bf7d4ddc Fix CQS signal facebook-unused-include-check in
fbcode/faiss/gpu (#4390)
discard 300650ef90b Fix CQS signal facebook-unused-include-check in
fbcode/faiss/impl (#4395)
discard 08d23eff952 Disable failing test until we support CUDA 12.8 in CI
(#4392)
discard e654c5d12b1 GpuIndexBinaryCagra - Binary CAGRA index (#4331)
discard 153323247de Fix unreachable-break issue in
faiss/IndexAdditiveQuantizer.cpp +1 (#4391)
discard 2aa00c25a3f Fix CQS signal facebook-unused-include-check in
fbcode/faiss/utils (#4389)
discard 3a92697fa7c Add guarantee_connectivity parameter to GpuIndexCagra
(#4388)
discard 68258b3b5f8 fix IndexIVFFastScan ndis/nlist stat (#4383)
discard 8bc78049537 Let IndexShards Pass down SearchParams (#4387)
discard 8c1b7456f9c fix: update broken links (#4382)
discard c2886071a07 Add Virtual Destructor to FlatIndex Class (#4381)
discard 0e181070dd7 Fix incorrect constructor docstring for
IndexScalarQuantizer (#4350)
discard 043534c4c2b Change uint8_t* => const uint8_t* in
faiss::ZeroCopyIOReader (#4376)
discard 2bdf6e17afa Fix CQS signal facebook-unused-include-check in
fbcode/faiss/tests (#4375)
discard 040732fb8f0 Set code_size for more InvertedListScanner implementations
(#4365)
discard f94f83531df Improving variable name post codemod changes (#4369)
discard d3f004ea74d Adding unit tests for supporting pre-built KNN while using
`IndexNSG` (#4368)
discard 4c13a88a3fd Improve naming due to codemod (#4367)
discard 87318bda275 Fix input param for IndexIVFScalarQuantizer in
index_factory (#4358)
discard 7ebd133462f Fix openMP index bug (#4348)
discard feb467ad90f Pass in "own_invlists" to ivf index constructor (#4353)
discard 3d7659e4693 Use packaging.version for correct version parsing (#4330)
discard b0809a2bc95 Add new centroid_id_column to support
previous_assignment_table (#4343)
discard cdbf9b36868 Fix CQS signal. Id] 95408353 --
performance-faster-string-find in fbcode/faiss (#4345)
discard 048e9612ed4 Copy IVF Centroids to Host for CPU Quantizer (#4336)
discard e8ced6e029c cmake: install missing header `impl/zerocopy_io.h` (#4328)
discard 8e415fe3540 Fix CQS signal. Id] 62183176 --
readability-redundant-string-init in fbcode/faiss/impl (#4332)
discard faa5c852342 Expose IndexBinaryIVF to C API (#4302)
discard e5902b00b5b Fix CQS signal. Id] 57328835 --
performance-unnecessary-value-param in fbcode/faiss/impl (#4329)
discard 7f13b602f01 Add rabitq bench to source control (#4307)
discard 4c405914919 Fix IndexBinaryIVF::merge_from (#4305)
discard 82cf65aeeb4 FreeBSD compatibility patch (#4316)
discard 3746ec322e9 Disable flaky ivfflat test_mem_leak
discard 4c5d342cc90 Update Swig File for CAGRA Params (#4314)
This update removed existing revisions from the reference, leaving the
reference pointing at a previous point in the repository history.
* -- * -- N refs/heads/faiss (ea1cdf0fb28)
\
O -- O -- O (8bb97aa85c0)
Any revisions marked "omit" are not gone; other references still
refer to them. Any revisions marked "discard" are gone forever.
No new revisions were added by this update.
Summary of changes:
.github/actions/build_cmake/action.yml | 2 +-
.github/workflows/build-pull-request.yml | 2 +-
.github/workflows/build-release.yml | 21 +-
.github/workflows/nightly.yml | 20 +-
CMakeLists.txt | 1 -
INSTALL.md | 13 +-
benchs/bench_6bit_codec.cpp | 3 +-
benchs/bench_cppcontrib_sa_decode.cpp | 3 +-
benchs/bench_fw/benchmark_io.py | 2 +-
benchs/bench_fw/descriptors.py | 5 -
benchs/bench_hamming_computer.cpp | 6 +-
benchs/bench_rabitq.py | 337 ---------------
c_api/CMakeLists.txt | 1 -
c_api/IndexBinaryIVF_c.cpp | 121 ------
c_api/IndexBinaryIVF_c.h | 118 -----
c_api/faiss_c.h | 6 -
c_api/macros_impl.h | 6 -
cmake/thirdparty/fetch_rapids.cmake | 5 +-
conda/faiss-gpu-cuvs/meta.yaml | 13 +-
conda/faiss-gpu/meta.yaml | 4 +-
conda/faiss/build-lib.bat | 4 +-
conda/faiss/build-pkg.bat | 4 +-
conda/faiss/meta.yaml | 4 +-
contrib/torch_utils.py | 55 +--
faiss/AutoTune.cpp | 65 ++-
faiss/CMakeLists.txt | 1 -
faiss/Clustering.cpp | 6 +-
faiss/IVFlib.cpp | 21 +-
faiss/Index.h | 71 ----
faiss/Index2Layer.cpp | 4 +-
faiss/IndexAdditiveQuantizer.cpp | 26 +-
faiss/IndexAdditiveQuantizer.h | 11 -
faiss/IndexBinary.h | 46 --
faiss/IndexBinaryFlat.cpp | 15 -
faiss/IndexBinaryFlat.h | 9 -
faiss/IndexBinaryHNSW.cpp | 40 +-
faiss/IndexBinaryHNSW.h | 22 -
faiss/IndexBinaryIVF.cpp | 25 +-
faiss/IndexBinaryIVF.h | 6 +-
faiss/IndexFastScan.cpp | 15 -
faiss/IndexFastScan.h | 9 -
faiss/IndexFlat.cpp | 35 +-
faiss/IndexFlat.h | 17 -
faiss/IndexFlatCodes.cpp | 15 -
faiss/IndexFlatCodes.h | 9 -
faiss/IndexHNSW.cpp | 138 ++----
faiss/IndexHNSW.h | 39 +-
faiss/IndexIDMap.cpp | 106 +----
faiss/IndexIDMap.h | 20 -
faiss/IndexIVF.cpp | 65 +--
faiss/IndexIVF.h | 32 +-
faiss/IndexIVFAdditiveQuantizer.cpp | 100 +----
faiss/IndexIVFAdditiveQuantizer.h | 24 +-
faiss/IndexIVFAdditiveQuantizerFastScan.cpp | 54 +--
faiss/IndexIVFAdditiveQuantizerFastScan.h | 22 +-
faiss/IndexIVFFastScan.cpp | 39 +-
faiss/IndexIVFFastScan.h | 6 +-
faiss/IndexIVFFlat.cpp | 117 ++---
faiss/IndexIVFFlat.h | 18 +-
faiss/IndexIVFPQ.cpp | 19 +-
faiss/IndexIVFPQ.h | 9 +-
faiss/IndexIVFPQFastScan.cpp | 20 +-
faiss/IndexIVFPQFastScan.h | 3 +-
faiss/IndexIVFPQR.cpp | 18 +-
faiss/IndexIVFPQR.h | 3 +-
faiss/IndexIVFRaBitQ.cpp | 31 +-
faiss/IndexIVFRaBitQ.h | 9 +-
faiss/IndexIVFSpectralHash.cpp | 11 +-
faiss/IndexIVFSpectralHash.h | 3 +-
faiss/IndexLattice.cpp | 12 +-
faiss/IndexNNDescent.cpp | 26 +-
faiss/IndexNNDescent.h | 11 +-
faiss/IndexNSG.cpp | 6 +-
faiss/IndexPQ.cpp | 58 ---
faiss/IndexPQ.h | 29 --
faiss/IndexPQFastScan.cpp | 2 +
faiss/IndexPreTransform.cpp | 28 +-
faiss/IndexPreTransform.h | 10 -
faiss/IndexRefine.cpp | 17 +-
faiss/IndexScalarQuantizer.cpp | 38 +-
faiss/IndexScalarQuantizer.h | 22 +-
faiss/IndexShards.cpp | 13 +-
faiss/MatrixStats.cpp | 24 +-
faiss/MetaIndexes.cpp | 18 +-
faiss/MetricType.h | 5 +-
faiss/clone_index.cpp | 3 +-
faiss/cppcontrib/factory_tools.cpp | 6 -
faiss/gpu/CMakeLists.txt | 18 +-
faiss/gpu/GpuAutoTune.cpp | 13 +-
faiss/gpu/GpuCloner.cpp | 40 +-
faiss/gpu/GpuIndex.cu | 544 +++++++-----------------
faiss/gpu/GpuIndex.h | 88 ----
faiss/gpu/GpuIndexBinaryCagra.cu | 406 ------------------
faiss/gpu/GpuIndexBinaryCagra.h | 133 ------
faiss/gpu/GpuIndexBinaryFlat.cu | 17 +-
faiss/gpu/GpuIndexBinaryFlat.h | 9 -
faiss/gpu/GpuIndexCagra.cu | 507 +++++-----------------
faiss/gpu/GpuIndexCagra.h | 37 +-
faiss/gpu/GpuIndexFlat.cu | 27 --
faiss/gpu/GpuIndexFlat.h | 15 -
faiss/gpu/GpuIndexIVF.cu | 28 +-
faiss/gpu/GpuIndexIVF.h | 14 -
faiss/gpu/GpuIndexIVFFlat.cu | 23 +-
faiss/gpu/GpuIndexIVFFlat.h | 1 -
faiss/gpu/GpuIndexIVFPQ.cu | 18 +-
faiss/gpu/GpuIndexIVFPQ.h | 1 -
faiss/gpu/GpuIndexIVFScalarQuantizer.cu | 7 -
faiss/gpu/GpuIndexIVFScalarQuantizer.h | 1 -
faiss/gpu/impl/BinaryCuvsCagra.cu | 291 -------------
faiss/gpu/impl/BinaryCuvsCagra.cuh | 118 -----
faiss/gpu/impl/CuvsCagra.cu | 87 ++--
faiss/gpu/impl/CuvsCagra.cuh | 22 +-
faiss/gpu/impl/CuvsIVFFlat.cu | 6 +-
faiss/gpu/impl/Distance.cu | 3 +-
faiss/gpu/impl/Distance.cuh | 17 -
faiss/gpu/impl/DistanceUtils.cuh | 57 ---
faiss/gpu/impl/FlatIndex.cuh | 3 -
faiss/gpu/impl/IndexUtils.cu | 17 +-
faiss/gpu/impl/IndexUtils.h | 6 +-
faiss/gpu/test/CMakeLists.txt | 2 -
faiss/gpu/test/TestGpuFilterConvert.cu | 251 -----------
faiss/gpu/test/TestGpuIndexBinaryCagra.cu | 411 ------------------
faiss/gpu/test/TestGpuIndexBinaryFlat.cpp | 2 +-
faiss/gpu/test/TestGpuIndexCagra.cu | 430 -------------------
faiss/gpu/test/TestGpuIndexFlat.cpp | 5 +-
faiss/gpu/test/test_binary_cagra.py | 90 ----
faiss/gpu/test/test_cagra.py | 164 +------
faiss/gpu/test/test_cuvs.py | 15 -
faiss/gpu/test/test_gpu_basics.py | 95 -----
faiss/gpu/utils/CuvsFilterConvert.cu | 230 ----------
faiss/gpu/utils/CuvsFilterConvert.h | 41 --
faiss/impl/AuxIndexStructures.cpp | 9 +-
faiss/impl/HNSW.cpp | 53 +--
faiss/impl/IDSelector.cpp | 3 +-
faiss/impl/LocalSearchQuantizer.cpp | 5 +-
faiss/impl/NNDescent.cpp | 26 +-
faiss/impl/PolysemousTraining.cpp | 63 +--
faiss/impl/ResultHandler.h | 103 ++---
faiss/impl/ScalarQuantizer.cpp | 43 +-
faiss/impl/index_read.cpp | 37 +-
faiss/impl/index_write.cpp | 12 +-
faiss/impl/io.cpp | 14 +-
faiss/impl/lattice_Zn.cpp | 29 +-
faiss/impl/mapped_io.cpp | 11 +-
faiss/impl/pq4_fast_scan.cpp | 1 +
faiss/impl/pq4_fast_scan_search_qbs.cpp | 1 +
faiss/impl/residual_quantizer_encode_steps.cpp | 12 +-
faiss/impl/zerocopy_io.cpp | 2 +-
faiss/impl/zerocopy_io.h | 4 +-
faiss/index_factory.cpp | 82 ++--
faiss/index_factory.h | 10 +-
faiss/python/CMakeLists.txt | 2 +-
faiss/python/__init__.py | 4 +-
faiss/python/class_wrappers.py | 51 +--
faiss/python/loader.py | 14 +-
faiss/python/setup.py | 3 +-
faiss/python/swigfaiss.swig | 5 -
faiss/utils/distances_fused/distances_fused.cpp | 4 +-
faiss/utils/distances_fused/simdlib_based.cpp | 2 +-
faiss/utils/extra_distances-inl.h | 31 +-
faiss/utils/quantize_lut.cpp | 2 +-
faiss/utils/utils.cpp | 3 +
perf_tests/CMakeLists.txt | 1 -
perf_tests/bench_scalar_quantizer_accuracy.cpp | 3 +-
perf_tests/bench_scalar_quantizer_encode.cpp | 1 +
tests/test_cppcontrib_sa_decode.cpp | 26 +-
tests/test_dealloc_invlists.cpp | 3 +-
tests/test_extra_distances.py | 155 +------
tests/test_factory_tools.cpp | 2 -
tests/test_fast_scan.py | 1 -
tests/test_graph_based.py | 57 +--
tests/test_hnsw.cpp | 15 +-
tests/test_index.py | 22 +-
tests/test_local_search_quantizer.py | 3 -
tests/test_lowlevel_ivf.cpp | 47 +-
tests/test_mem_leak.cpp | 1 -
tests/test_pairs_decoding.cpp | 9 +-
tests/test_params_override.cpp | 12 +-
tests/test_sliding_ivf.cpp | 9 +-
tutorial/cpp/1-Flat.cpp | 18 +-
tutorial/cpp/2-IVFFlat.cpp | 12 +-
tutorial/cpp/3-IVFPQ.cpp | 15 +-
tutorial/cpp/4-GPU.cpp | 18 +-
tutorial/cpp/5-Multiple-GPUs.cpp | 12 +-
tutorial/cpp/6-HNSW.cpp | 12 +-
tutorial/python/10-FaissCuvsExample.ipynb | 258 -----------
186 files changed, 1073 insertions(+), 7048 deletions(-)
delete mode 100644 benchs/bench_rabitq.py
delete mode 100644 c_api/IndexBinaryIVF_c.cpp
delete mode 100644 c_api/IndexBinaryIVF_c.h
delete mode 100644 faiss/gpu/GpuIndexBinaryCagra.cu
delete mode 100644 faiss/gpu/GpuIndexBinaryCagra.h
delete mode 100644 faiss/gpu/impl/BinaryCuvsCagra.cu
delete mode 100644 faiss/gpu/impl/BinaryCuvsCagra.cuh
delete mode 100644 faiss/gpu/test/TestGpuFilterConvert.cu
delete mode 100644 faiss/gpu/test/TestGpuIndexBinaryCagra.cu
delete mode 100644 faiss/gpu/test/test_binary_cagra.py
delete mode 100644 faiss/gpu/utils/CuvsFilterConvert.cu
delete mode 100644 faiss/gpu/utils/CuvsFilterConvert.h
delete mode 100644 tutorial/python/10-FaissCuvsExample.ipynb
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
