注册并分享邀请链接,可获得视频播放与邀请奖励。

turbopuffer
@turbopuffer
search built on object storage. fast, cheap, petabyte-scale. powers Anthropic, Harvey, Notion, Cognition, and more
加入 October 2023
6 正在关注    18.1K 粉丝
new: i8 vectors f32: 4 bytes/dim i8: 1 byte/dim 4x fewer bytes → 75% lower storage and query costs + faster queries when embedded with a quantization-aware model (e.g. voyage-4-large) trained on i8 vectors, recall loss can be ~0! docs:
显示更多
0
2
160
11
转发到社区