pg.ddx.io  pgvector/pgvector GitHub issues and pull requests  
help / color / mirror / Atom feed
From: saolof (@saolof) <noreply+saolof@github.com>
To: pgvector/pgvector <noreply+pgvector-pgvector@github.com>
Subject: Re: [pgvector/pgvector] issue #1065: Support for Advanced K-means Acceleration Techniques in IVFFlat Index Construction
Date: Tue, 17 Nov 2026 19:12:58 +0000
Message-ID: <gh-pgvector-pgvector-1065-c6958194556@github.com> (raw)
In-Reply-To: <gh-pgvector-pgvector-1065@github.com>
References: <gh-pgvector-pgvector-1065@github.com>

Apart from the e-means EMA trick, quantized k-means is another trick to speed up k-means on disk. Rabitq-quantize the vectors first, and run k-means/e-means using the quantized distances to include more points earlier for a given amount of disk traffic. 

If you combine it with e-means there are a few variations on that idea like doing the initial iteration using the full vectors and combining that with the pass that generates the quantized vectors, then combining the e-means passes through the quantized vectors with the rearrangement into posting lists.

view thread (4+ messages)

Message-ID: <gh-pgvector-pgvector-1065-c6958194556@github.com>
Permalink:  ../gh-pgvector-pgvector-1065-c6958194556@github.com/

 · 


This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox