pg.ddx.io  pgvector/pgvector GitHub issues and pull requests  
help / color / mirror / Atom feed
From: R3gardless (@R3gardless) <noreply+R3gardless@github.com>
To: pgvector/pgvector <noreply+pgvector-pgvector@github.com>
Subject: Re: [pgvector/pgvector] issue #1003: Support RabitQ in pgvector
Date: Fri, 18 Sep 2026 09:59:17 +0000
Message-ID: <gh-pgvector-pgvector-1003-c5728401624@github.com> (raw)
In-Reply-To: <gh-pgvector-pgvector-1003@github.com>
References: <gh-pgvector-pgvector-1003@github.com>

@zthhhhh Hi, I'm interested in this implementation!

The performance gains look great, but the smaller indexes caught my eye just as much. RAM is expensive, so getting the HNSW index down to about a third of its original size seems pretty valuable on its own, even without a huge speedup. More room in cache and one less reason to ask for a bigger server :)

Would be interesting to see how it performs when the original index doesn't fit in memory but the quantized one does. Thanks for sharing!

view thread (12+ messages)  latest in thread

Message-ID: <gh-pgvector-pgvector-1003-c5728401624@github.com>
Permalink:  ../gh-pgvector-pgvector-1003-c5728401624@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