SVS v0.4.0

What's Changed

• Native serialization support for Indexes (#300)

• Clang-21 compiler support with gcc-11 headers for shared library builds

• Amazonlinux2 support for shared/static library dropped

• Consolidated to publish only minimal necessary shared library (14 -> 6) and runtime bindings (2 -> 1) release artifacts

• Adaptive batch size heuristic for filtered search in Vamana, with new filter_stop early-exit parameter (#309)

• IVF runtime support for IDFilter-based filtered search and dynamic set_intra_query_threads adjustment after train()/load() (#322)

• IVF inter-query thread pool initialization now validates and clamps thread count against the number of centroids (#329)

• In-memory (mmap) stream index mapping with new map_to_file and map_to_memory APIs on FlatIndex and VamanaIndex (#310)

• Add get_distance and reconstruct_at to VamanaIndex API (#315)

Full Changelog: v0.3.0...v0.4.0

v0.3.0

What's Changed

• IVF index support added to CPP runtime API (#267, #287, #293)

Full Changelog: v0.2.0...v0.3.0

v0.2.0

What's Changed

• IVF, including Dynamic IVF Index Implementation (#223), batch iterator in IVF (#247), Save/Load functionality with dense clusters (#260)

• LeanVec OOD added to C++ Runtime Bindings (#264)

• Addition of libsvs-runtime conda package for SVS C++ Runtime Bindings (#255)

• Adds LVQ8x0 support to CPP Runtime API (#252)

• Custom index block size enabled in C++ Runtime Bindings (#248)

Full Changelog: v0.1.0...v0.2.0

nightly

Rolling releases and nightly builds. Assets in this release can be deleted at any time. The nightly tag itself can also change at any time.

Recommended formatting is {default name of artifact}-nightly-{YYYY}-{MM}-{DD}-{GH actions run ID}.{file type} - for example a runtime bindings tarball uploaded on Jan 2 2026 from run #1416 (see image below) would be named svs-cpp-runtime-bindings-nightly-2026-01-02-1416.tar.gz

v0.1.0

What's Changed

• Creation of SVS C++ Runtime Bindings package (#208)
• Addition of libsvs conda and python packages along with existing tarballs
• Added shared library support for Clang-20
• LVQ8x8 support added to SVS python package
• Fixes related to VamanaBuildParameters (#237) and unmasked AVX2 load (#239)

Full Changelog: v0.0.11...v0.1.0

v0.0.11

What's Changed

IVF support for SQDataset (#184), LVQ, and LeanVec

Various bug resolutions, fixes, and tooling support

Full Changelog: v0.0.10...v0.0.11

v0.0.10

What's Changed

• Support for OpenMP threading (#170, #171, #172)
• Enable Inverted File index (#156)
• Resolution of inf/nan crashes in LVQ (#174, #178)
• SVS_LAZY update to address alpine issue (#175)
• Updates to build parameter defaults (#176)
• MKL symbols not exported from SVS libs

Full Changelog: v0.0.9...v0.0.10

v1.0.0-dev

Rolling release page for next major release, 1.0.0. This page provides nightly builds with the latest commits to main. See v0.0.9...main

v0.0.9

What's Changed

• fix: Multi-vector dynamic vamana index Save/Load functionality by @rfsaliev in #162
• feature: save and load in flat index by @yuejiaointel in #163
• Handle corner in dynamic index with insufficient valid search results by @ibhati in #164
• change to v0.0.9 by @ahuber21 in #169

Full Changelog: v0.0.8...v0.0.9

v0.0.8

• Addition of 8-bit scalar quantization support to C++ interface

• Introduced multi-vector index and batch iterator support that allows multiple vectors to be mapped to the same external ID

• Automatic ISA dispatching with optimizations based on AVX support

• Enabled compatibility with ARM and MacOS

• Enhanced logging capabilities

• Updated vamana iterator API

• Broader shared library support:

  • gcc-11+, clang-18+, glibc 2.26+ compatibility

  • Static library provided in addition to .so

  • Intel(R) MKL linked within the shared library - no need for Intel(R) MKL in user environment

Note

SVS shared and static libraries are included in the tarballs. Binary variants included in this release:

• svs-shared-library-0.0.8.tar.gz: Standard build for GCC 11+ and glibc 2.28+ — compatible with most modern Linux distributions
• glibc2_26 suffix: Build for GCC 11+ and glibc 2.26 (e.g. Amazon Linux 2)
• clang suffix: Build for Clang-18+
• reduced suffix: Lighter-weight builds for specific integrations — not recommended for general use