SuperEMeans: Making e-means 3脳 faster

SuperEMeans: Making e-means 3脳 faster

TL;DR: We fused SuperKMeans and e-means, resulting in 3脳 faster clustering of high-dimensional vectors without quality trade-offs. Available now at https://github.com/cwida/SuperKMeans. Recently, there has been a lot of buzz around clustering of vector embeddings: EV艒C, SuperKMeans, QGKmeans, and just last week, e-means, o-means, and s-means. Among these, e-means is a big deal: it promises the same quality as Lloyd鈥檚 with only 2 epochs. Why is this a big deal for vector search? Well, clustering is a key building block for large-scale vector indexes (e.g., IVF, ScANN), which is precisely the bottleneck that users have to wait on before issuing similarity search queries. ...

November 17, 2026 路 6 min 路 1199 words 路 Leonardo Kuffo
Indexing 10M vector embeddings in 1 minute on a single CPU

Indexing 10M vector embeddings in 1 minute on a single CPU

Indexing large vector embedding collections remains a pain point when setting up vector search infrastructures. Indexes like HNSW or IVF can take hours or even days to construct. To tackle this issue, we have developed and open-sourced SuperKMeans, a super-fast clustering library for high-dimensional vector embeddings that drastically reduces indexing time from hours to mere seconds. In this blog post, I will show how SuperKMeans can index 10 million 1024-dimensional vector embeddings in just 1 minute on a single CPU. Additionally, I will explain the secret sauce behind SuperKMeans鈥檚 extremely fast clustering performance. ...

February 19, 2026 路 7 min 路 1479 words 路 Leonardo Kuffo