Research talk: SPTAG++: Fast hundreds of billions-scale vector search with millisecond response time
589
10.9
Microsoft Research329 тыс
Следующее
25.01.22 – 1712:08Популярные
Опубликовано 25 января 2022, 1:37
Speaker: Qi Chen, Senior Researcher, Microsoft Research Asia
Current state-of-the-art vector approximate nearest neighbor search (ANNS) libraries mainly focus on how to do fast high-recall search in memory. However, extremely large-scale vector search scenarios present certain challenges. For example, hundreds of billions of vectors coupled with limited memory creates a capacity issue. There is also a scalability issue because increasing the number of serving machines increases query latency and computation costs. This occurs as a result of the search being done in each machine, and latency increases with the increased number of aggregating candidates. To address these challenges, we propose SPTAG++, a distributed ANNS system. In this talk, we’ll discuss SPTAG++, which is now integrated into production to support hundreds of billions-scale vector searches in production with millisecond response time and more than ten thousand queries per second.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Current state-of-the-art vector approximate nearest neighbor search (ANNS) libraries mainly focus on how to do fast high-recall search in memory. However, extremely large-scale vector search scenarios present certain challenges. For example, hundreds of billions of vectors coupled with limited memory creates a capacity issue. There is also a scalability issue because increasing the number of serving machines increases query latency and computation costs. This occurs as a result of the search being done in each machine, and latency increases with the increased number of aggregating candidates. To address these challenges, we propose SPTAG++, a distributed ANNS system. In this talk, we’ll discuss SPTAG++, which is now integrated into production to support hundreds of billions-scale vector searches in production with millisecond response time and more than ten thousand queries per second.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Свежие видео
10 дней – 8474:31
11 дней – 1 784 81015:02
16 дней – 1760:30
16 дней – 6750:23
17 дней – 2 050 5309:41Случайные видео
57 дней – 1298:50
131 день – 19 02528:52
24.03.23 – 3 5721:29
31.10.22 – 31 21528:37
06.02.21 – 1 2624:08
05.05.20 – 4 1341:45
1 день – 6274:37
3 дня – 5980:31
4 дня – 2 4520:51
5 дней – 2511:04
7 дней – 8 0230:16
9 дней – 1 2660:24
3 дня – 4587:37
3 дня – 4 7151:26