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 |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| TestGpuIndexFlat.cpp | ||
| TestGpuIndexIVFFlat.cpp | ||
| TestGpuIndexIVFPQ.cpp | ||
| TestGpuSelect.cu | ||
| TestUtils.cpp | ||
| TestUtils.h | ||
| demo_ivfpq_indexing_gpu.cpp | ||
| test_gpu_index.py | ||