9 releases (breaking)

0.7.0 Jul 18, 2021
0.6.0 Feb 21, 2021
0.5.1 Aug 15, 2020
0.5.0 Jul 26, 2020
0.1.1 Feb 14, 2019
Download history 90/week @ 2021-06-22 249/week @ 2021-06-29 215/week @ 2021-07-06 294/week @ 2021-07-13 192/week @ 2021-07-20 198/week @ 2021-07-27 98/week @ 2021-08-03 66/week @ 2021-08-10 72/week @ 2021-08-17 70/week @ 2021-08-24 112/week @ 2021-08-31 94/week @ 2021-09-07 166/week @ 2021-09-14 242/week @ 2021-09-21 169/week @ 2021-09-28 130/week @ 2021-10-05

645 downloads per month
Used in 9 crates (4 directly)

Apache-2.0

71KB
1.5K SLoC

Reductive

Training of optimized product quantizers

Training of optimized product quantizers requires a LAPACK implementation. For this reason, training of the OPQ and GaussianOPQ quantizers is feature-gated by the opq-train feature. This feature must be enabled if you want to use OPQ or GaussianOPQ:

[dependencies]
reductive = { version = "0.7", features = ["opq-train"] }

This also requires that a crate that links a LAPACK library is added as a dependency, e.g. accelerate-src, intel-mkl-src, openblas-src, or netlib-src.

Running tests

Linux

You can run all tests on Linux, including tests for optimized product quantizers, using the intel-mkl-test feature:

$ cargo test --features intel-mkl-test

macOS

All tests can be run on macOS with the accelerate-test feature:

$ cargo test --features accelerate-test

Multi-threaded OpenBLAS

reductive uses Rayon to parallelize quantizer training. However, multi-threaded OpenBLAS is known to conflict with application threading. Is you use OpenBLAS, ensure that threading is disabled, for instance by setting the number of threads to 1:

$ export OPENBLAS_NUM_THREADS=1

Dependencies

~3–12MB
~184K SLoC