faiss/gpu/test
Lucas Hosseini 76bec0b500
Facebook sync (#573)
Features:

- automatic tracking of C++ references in Python
- non-intel platforms supported -- some functions optimized for ARM
- override nprobe for concurrent searches
- support for floating-point quantizers in binary indexes
Bug fixes:

- no more segfaults in python (I know it's the same as the first feature but it's important!)
- fix GpuIndexIVFFlat issues for float32 with 64 / 128 dims
- fix sharding of flat indexes on GPU with index_cpu_to_gpu_multiple
2018-08-30 19:38:50 +02:00
..
CMakeLists.txt Rename gpu/tests to gpu/test (#481) 2018-06-06 14:08:49 +02:00
Makefile Rename gpu/tests to gpu/test (#481) 2018-06-06 14:08:49 +02:00
TestGpuIndexFlat.cpp Facebook sync (#573) 2018-08-30 19:38:50 +02:00
TestGpuIndexIVFFlat.cpp Facebook sync (#573) 2018-08-30 19:38:50 +02:00
TestGpuIndexIVFPQ.cpp Facebook sync (#573) 2018-08-30 19:38:50 +02:00
TestGpuSelect.cu Facebook sync (#573) 2018-08-30 19:38:50 +02:00
TestUtils.cpp Facebook sync (#504) 2018-07-06 14:12:11 +02:00
TestUtils.h Facebook sync (#504) 2018-07-06 14:12:11 +02:00
demo_ivfpq_indexing_gpu.cpp Rename gpu/tests to gpu/test (#481) 2018-06-06 14:08:49 +02:00
test_gpu_index.py Facebook sync (#573) 2018-08-30 19:38:50 +02:00
test_pytorch_faiss.py Rename gpu/tests to gpu/test (#481) 2018-06-06 14:08:49 +02:00