mirrors
/
faiss
mirror of https://github.com/facebookresearch/faiss.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
301 Commits
23 Branches
19 Tags
212 MiB
Commit Graph

301 Commits (a8e4c5e2d5a4f93669338f4855cda980853014cc)
 

Author SHA1 Message Date
Lucas Hosseini a8e4c5e2d5 Move build to CMake (#1313) 
Summary: Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1313

Reviewed By: mdouze

Differential Revision: D22948267

Pulled By: beauby

fbshipit-source-id: ec16fa0342f37672d46fb7886ecc55c7996011c4
 2020-08-14 15:03:10 -07:00
Matthijs Douze 4c3b5ad156 Add missing downcast (#1330) 
Summary:
Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1330

add missing downcast for Index (and test for github sync)

See github issue https://github.com/facebookresearch/faiss/issues/1278

Reviewed By: beauby

Differential Revision: D23053182

fbshipit-source-id: 1ce4c248342332ce632ecfd5074affa3ddf55b66
 2020-08-13 16:37:58 -07:00
Lucas Hosseini 569c855ed0 Fix guard clauses for SSE3. (#1325) 
Summary: Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1325

Reviewed By: mdouze

Differential Revision: D23104964

Pulled By: beauby

fbshipit-source-id: 04705f1695e65682748b6308fd5d3e217a4af75a
 2020-08-13 10:10:19 -07:00
kfoldcrossvalidator 13a2d4ef8f Update INSTALL.md (#1222) 
Summary:
Added a quotation mark here, so copy and pasting works.

Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1222

Reviewed By: patricklabatut

Differential Revision: D23002083

Pulled By: beauby

fbshipit-source-id: e92b07a5326b3b79f035e8869937d853bec1df69
 2020-08-07 11:10:59 -07:00
imlidian bc52661468 fixed. wrong python path on install doc (#1321) 
Summary: Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1321

Reviewed By: patricklabatut

Differential Revision: D22999873

Pulled By: beauby

fbshipit-source-id: 28696e8f7bb9e2bf6a8092b19853ac331415f810
 2020-08-07 08:46:52 -07:00
Lucas Hosseini b23cb289d3 Fix AVX2 preprocessor guard. (#1317) 
Summary:
Some avx2 function calls were guarded with `__AVX__` instead of `__AVX2__`.

Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1317

Reviewed By: patricklabatut

Differential Revision: D22981635

Pulled By: beauby

fbshipit-source-id: 79ac3184bd32c94bc75a4c3118ae8cd2ea187fe3
 2020-08-06 13:41:38 -07:00
Lucas Hosseini ac74f576f7 fbshipit-source-id: 4f3cfa59471d548af93fe118d1b73d45bc648edf 2020-08-04 12:00:38 -07:00
Lucas Hosseini 31f27bd15a ShipIt sync. 
fbshipit-source-id: f8ed169dc1d95b3364f4a158efb9fae531a5901d
 2020-08-04 09:57:43 -07:00
Lucas Hosseini 750d43f7f1
Move source code to faiss/ subdirectory. (#1312) 
* Move source code to faiss/ subdirectory.

* Remove stale files.
 2020-08-04 17:16:58 +02:00
Lucas Hosseini cd38e82f0c
Facebook sync 2020-07-31 (#1308) 2020-08-03 22:15:02 +02:00
Yurij Mikhalevich a93a4b3957
python: fix faiss.ResultHeap (#1287) 
Fixes typos in `faiss.ResultHeap`.
 2020-07-27 17:27:07 +02:00
Eduardo Pinho bf593c0fae
[c_api] Fix GPU library build (#1296) 
- depend on libfaiss.so instead of libgpufaiss.so
- update include directives in gpu C wrapper impl
- fix implicit call warning in C examples
 2020-07-27 17:26:17 +02:00
glutamatt 9e5d5b722e
fix free parameterspace (#1243) 2020-07-09 09:32:03 +02:00
Wenhao Liu d76d26964c
Add missing header include (#1245) 
Add missing header include for index_gpu_to_cpu function
 2020-07-09 09:30:44 +02:00
Matthijs Douze 9258a9535e
fix datatypes for mac (#1270) 2020-06-28 13:00:44 +02:00
Matthijs Douze e8c8db85ae fix #1213 2020-06-02 13:59:39 -07:00
Nackel 833d417db1
Correct a spelling mistake (#1190) 
thanks
 2020-05-05 12:18:10 +02:00
Matthijs Douze c6bc8c46f1
Update README.md 2020-03-30 09:20:19 +02:00
Matthijs Douze a5b850dec6
Update README.md 2020-03-30 09:19:07 +02:00
Jeff Johnson f1fe029e0b Merge branch 'master' of https://github.com/facebookresearch/faiss 2020-03-29 20:07:03 -07:00
Jeff Johnson e05f773f3f CUDA 8 fixes 2020-03-29 20:07:01 -07:00
Jeff Johnson ba061ff82c CUDA 10 fixes 2020-03-30 03:01:56 +00:00
Matthijs Douze 817a3ac77d
Update INSTALL.md 2020-03-29 12:43:10 +02:00
Matthijs Douze a489faf7c6
Update README.md 2020-03-29 08:46:18 +02:00
Jeff Johnson 2a36d4d8c7 fix gpu/test Makefile 2020-03-26 21:56:32 +00:00
Jeff Johnson 64dd988443 remove deleted files from template change 2020-03-25 10:57:57 -07:00
Lucas Hosseini b9914eb30a Fix conda packages build reqs. 2020-03-25 18:16:37 +01:00
Lucas Hosseini a17a631dc3
Sync 20200323. (#1157) 
* Sync 20200323.

* Bump version.

* Remove warning filter.
 2020-03-24 14:06:48 +01:00
Brian Hart fc2a1c1775
Improve CPU architecture tolerance (#1142) 
numpy's CPU info dictionary does not have a 'flags' field on some
CPU architectures (such as ppc64le). Tolerate absence of 'flags'
when checking for instruction set to allow faiss to continue in
non-AVX2 mode on those architectures.
 2020-03-20 11:32:22 +01:00
glutamatt ddd9c52f31
C API : ClusteringIterationStats integration (#1140) 
Thanks for the fix @glutamatt and thanks for the review @Enet4 !

* C API : ClusteringIterationStats integration

* Update c_api/Clustering_c.h

Co-Authored-By: Eduardo Pinho <enet4mikeenet@gmail.com>

* Update c_api/Clustering_c.cpp

Co-Authored-By: Eduardo Pinho <enet4mikeenet@gmail.com>

* Update c_api/Clustering_c.cpp

Co-Authored-By: Eduardo Pinho <enet4mikeenet@gmail.com>

* Update c_api/Clustering_c.cpp

Co-Authored-By: Eduardo Pinho <enet4mikeenet@gmail.com>

* Add getter implementation

Co-authored-by: Eduardo Pinho <enet4mikeenet@gmail.com>
 2020-03-12 23:22:39 +01:00
Jeff Johnson 73b4e4db28
Merge pull request #1121 from wxingda/master 
Add .cuh files to install include dir.
 2020-03-10 13:13:15 -07:00
Lucas Hosseini 22b7876ef5
Facebook sync (2020-03-10) (#1136) 2020-03-10 14:24:07 +01:00
wxd 0559449827
Merge pull request #1 from wxingda/wxingda-patch-1 
Add cuh files to install include dir.
 2020-02-29 21:12:36 +08:00
wxd a93878ff73
Add cuh files to install include dir. 
Add cuh files to install include dir to enable cuda testing for user.
 2020-02-29 21:09:50 +08:00
Andrei Ruslantsev 053dc46036
Add support to use selected GPUs by id (#1065) 
* Add support to use selected GPUs by id

One can pass parameter gpus to index_cpu_to_gpus_list to use only selected GPU's, i.e. if we pass gpus=[1, 3, 4], we will use 1-st, 3-rd and 4-th graphical cards

* merge functions to avoid code duplication

* use first gpus if none passed
 2020-02-25 10:17:15 +01:00
glutamatt 5a187120a5
[ C api ] Indexpretransform get underlying index (#1100) 
Approved by @Enet4 so good by me.
 2020-02-10 15:00:59 +01:00
Danil Guskov 7e08db7cb7
c_api: faiss_IndexIVF_invlists_get_ids function (#1094) 
If @Enet4 approves it's fine with me.

* c_api: faiss_IndexIVF_invlists_get_ids function

* Update c_api/IndexIVF_c.h

Co-Authored-By: Eduardo Pinho <enet4mikeenet@gmail.com>

Co-authored-by: Eduardo Pinho <enet4mikeenet@gmail.com>
 2020-01-31 13:40:28 +01:00
Matthijs Douze e0849496dd
Update README.md 2020-01-20 11:00:45 +01:00
Matthijs Douze 1a332509a3
Update 5-Multiple-GPUs.cpp 
Thanks to gameofdimension
https://github.com/facebookresearch/faiss/pull/1060/files
 2020-01-16 16:46:11 +01:00
glutamatt d278355b9c Fix typo in Clustering_c.h (#1084) 2020-01-14 15:41:07 +01:00
Matthijs Douze 281c9f7113
fixing typedef 
see #1064
 2020-01-03 07:19:07 +01:00
Matthijs Douze c250587c77
Update README.md 2019-12-09 13:32:36 +00:00
Lucas Hosseini 2ba6985f81 Facebook sync 20191129 (#1048) 
Looks good!
 2019-12-04 07:21:02 +01:00
Kota Yamaguchi 83a341f300 Replace print with logging (#964) 2019-11-21 11:42:03 +01:00
Lucas Hosseini da24fcc56e
Use intrinsics for float16 in GPU scalar quantizer. (#987) 2019-11-19 16:15:33 +01:00
mattg-sp 2ab4b4859c Fixes to enable building with -mavx, for Sandybridge CPUs. (#992) 
The -mf16c (i.e. packed-half conversion instructions) weren't added until the
Ivy Bridge CPU generation (https://en.wikipedia.org/wiki/F16C#CPUs_with_F16C).
Therefore, code dependent on those intrinsics must be conditioned on __F16C__ -
not __AVX__.
 2019-11-19 16:15:00 +01:00
Jose Truyol c47da8a948 [C_API] Pass compilation in current state (#989) 
* Pass compilation in current state

* Fix formatting and add missing parts

* Define DistanceComputer

* Add documentation to name changed on DistanceComputer::operator()()

* Apply suggestions from code review

Changes in docs

Co-Authored-By: Eduardo Pinho <enet4mikeenet@gmail.com>

* Updated MetricType
 2019-11-19 11:36:44 +01:00
Matthijs Douze 4c32fa4d14
Update demo_sift1M.cpp 2019-11-19 11:18:47 +01:00
Jin Hai e325c50e97 fix bugs with setNumProbes in GPUIndexIVF (#1011) 2019-11-10 07:37:06 +01:00
Jeff Johnson 2cce2e5f59
Merge pull request #1006 from milvus-io/1.6.0 
Fix GPUSQ copyto bug
 2019-10-31 23:57:57 -04:00