784e2facd8
* 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 |
||
|---|---|---|
| .. | ||
| demo_auto_tune.py | ||
| demo_ivfpq.py | ||
| swigfaiss.py | ||
| swigfaiss_gpu.py | ||
| swigfaiss_gpu_wrap.cxx | ||
| swigfaiss_wrap.cxx | ||