yesterday we processed 10B+ vector/document writes (~40TB) that's 100,000+ writes per second sustained
turbopuffer
科技、信息和网络
built on top of object storage, which means 10x-100x cheaper, usage-based pricing, and massive scalability
关于我们
- 网站
-
https://turbopuffer.com
turbopuffer的外部链接
- 所属行业
- 科技、信息和网络
- 规模
- 2-10 人
- 类型
- 私人持股
turbopuffer员工
动态
-
changelog for february! ?? https://lnkd.in/eTVNvKs5
-
-
every time we re-run the landing page benchmarks, they improve slightly. (bars are off because these are simply website screenshots) https://turbopuffer.com/ by default, turbopuffer does consistent reads, but you can switch to eventual consistency for even faster queries.
-
-
A summary of what we shipped in January ?? https://lnkd.in/eTVNvKs5
-
-
changelog for november & december ?????? https://lnkd.in/eTVNvKs5
-
-
what team tpuf shipped in September: ?? SOC 2 Type 2 ?? Blog post on Continuous Recall Measurement ?? 8 MiB attribute value limit (up from 64 KiB) ?? Add copy_from_namespace to create a namespace by copying another namespace (50% discount relative to upserting from scratch) ?? Add uuid type (55% discount from string) and bool type https://lnkd.in/eTVNvKs5
-
Our first blog post is out "turbopuffer: fast search on object storage" https://lnkd.in/g3CGHhpK