• matthijs's avatar
    * moved most FAISS_ASSERT calls to C++ exceptions, and adjusted · aa1585cb
    matthijs authored
      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
    aa1585cb
Name
Last commit
Last update
..
CMakeLists.txt Loading commit data...
demo_imi_flat.cpp Loading commit data...
demo_imi_pq.cpp Loading commit data...
demo_ivfpq_indexing.cpp Loading commit data...
demo_sift1M.cpp Loading commit data...
test_blas.cpp Loading commit data...
test_build_blocks.py Loading commit data...
test_index.py Loading commit data...
test_ivfpq_codec.cpp Loading commit data...
test_ivfpq_indexing.cpp Loading commit data...