Research talk: SPTAG++: Fast hundreds of billions-scale vector search with millisecond response time
612
11.3
Microsoft Research334 тыс
Следующее
25.01.22 – 1732:08Популярные
39 дней – 28 5513:25
83 дня – 4 47715:12Опубликовано 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
5 дней – 3550:47
5 дней – 9 6303:24
5 дней – 12 7401:25
6 дней – 1 2720:32
9 дней – 1390:24Случайные видео
66 дней – 150 2170:31
252 дня – 9 2592:39
08.09.23 – 6 6660:54
10.08.22 – 1 394 54321:32
3 дня – 2 5660:54
6 дней – 482 7660:57
6 дней – 7 2752:08
6 дней – 5 2820:52
3 дня – 2 862 26617:49