註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

turbopuffer
@turbopuffer
search built on object storage. fast, cheap, petabyte-scale. powers Anthropic, Harvey, Notion, Cognition, and more
加入 October 2023
6 正在關注    18.1K 粉絲
tpuf quantizes vectors to improve perf (RaBitQ) the algo randomly rotates vectors, and we were using matmul at O(d²) space & time, brutal at high dims. 10k = 400MB in RAM! we rebuilt the rotation using FWHT at O(d) space & O(d log d) time. ~no recall loss, 10k = only 5kB in RAM
顯示更多
0
6
149
10
轉發到社區