Add leanvec_primary_only build option to C++ runtime#323
Draft
Conversation
Adds a new `leanvec_primary_only` parameter (default false) to the
LeanVec build entry points in the C++ runtime API:
- VamanaIndexLeanVec::build (both overloads)
- DynamicVamanaIndexLeanVec::build (DynamicIndexParams overloads)
The flag is stored in {Vamana,DynamicVamana}IndexLeanVecImpl and
forwarded through init_impl -> build_impl -> StorageFactory<LeanVec>::init
-> LeanDataset::reduce, where it skips secondary-dataset allocation
and disables reranking. ABI back-compat overloads are unchanged.
Compiles standalone with SVS_RUNTIME_HAVE_LVQ_LEANVEC=OFF (stub returns
NOT_IMPLEMENTED). When enabled, requires the matching LeanDataset::reduce
overload that accepts the primary_only argument (added in the private
repository alongside the LeanDataset save/load support).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a new
leanvec_primary_onlyparameter (defaultfalse) to the LeanVecbuild entry points in the C++ runtime API. When enabled, the LeanVec
secondary (full-precision) dataset is not allocated, roughly halving the
LeanVec memory footprint for workloads that don't need re-ranking.
API changes
A trailing
bool leanvec_primary_only = falseargument is added to:VamanaIndexLeanVec::build(both overloads)DynamicVamanaIndexLeanVec::build(theDynamicIndexParamsoverloads)Existing call sites are source- and ABI-compatible: the parameter is
defaulted, and the legacy back-compat overloads are unchanged.
Plumbing
The flag is stored in
{Vamana,DynamicVamana}IndexLeanVecImpland forwardedthrough
init_impl→build_impl→StorageFactory<LeanVec>::init→LeanDataset::reduce, where it skips secondary-dataset allocation anddisables re-ranking at search time.