Matthijs Douze

Results 23 issues of Matthijs Douze

by default use_raft is set to false, see https://github.com/facebookresearch/faiss/blob/main/faiss/python/gpu_wrappers.py#L59 It should be set to `use_raft='auto'` and decide at runtime using `get_compile_options()`. https://github.com/facebookresearch/faiss/blob/main/faiss/gpu/GpuIndex.cu#L532

enhancement
GPU

Add doc to the FAISS Wiki * New chapter in Faiss wiki * Add info about how CuVS is wrapped * Point back to CuVS doc where needed

GPU
documentation

See title. The removal should take place on the two indices. While we are there, check the behavior of filtered search. related: #3820

enhancement
Implementation
backlog

Summary: Allows factory strings like `IVF3k,Flat` as a shorthand for 3072 centroids. The main question is whether k or M should be metric (k=1000) or power of 2 (k=1024): *...

CLA Signed
fb-exported

Summary: External modules should work fine as plug-ins to Faiss in the following cases: * additional objects that can be passed in as callbacks to Faiss * functions that use...

CLA Signed
install
fb-exported

# Summary # Platform OS: Linux 64 intel Faiss version: 1.8.0 Installed from: conda Running on: CPU Interface: Python # Reproduction instructions The type mapping between c++ and Python integer...

enhancement
install
backlog

GPU search supports `search_preassigned` but not `add_preassigned` which is required when an arbitrary quantizer is used. https://github.com/facebookresearch/faiss/blob/main/faiss/gpu/GpuIndexIVF.h#L101 It would be useful to implement it.

GPU
feature request
backlog

Faiss does not transparently convert numpy int64 and float64 / float32 to SWIG's int and float ```python import faiss import numpy as np a = np.array([4, 6]) d = a[0]...

enhancement
install
backlog

For some use cases, Faiss serves only as a storage engine for flat arrays of compressed vectors. Maybe it would be useful to make a wrapper that makes this easier...

feature request
Implementation
backlog

Summary: C++ Faiss is compiled with (at least) 3 compilers: - the one compiling the main CPU Faiss - the one called by nvcc to compile host code on GPU...

CLA Signed
fb-exported
backlog