mirror of
https://github.com/facebookresearch/faiss.git
synced 2026-10-12 02:13:36 +00:00
* moved most FAISS_ASSERT calls to C++ exceptions, and adjusted memory allocation to avoid mem leaks * added an IndexIVFScalarQuantizer type that offers an intermediate compression between IVFFlat and IVFPQ * support removal of indices in IndexIDMap / IndexFlat combination * various fixes in GPU code