From: ankane (@ankane) <noreply+ankane@github.com>
To: pgvector/pgvector <noreply+pgvector-pgvector@github.com>
Subject: Re: [pgvector/pgvector] PR #1058: Improved performance of IVFFlat index scans
Date: Wed, 18 Nov 2026 00:06:46 +0000
Message-ID: <gh-pgvector-pgvector-1058-c6964769508@github.com> (raw)
In-Reply-To: <gh-pgvector-pgvector-1058@github.com>
References: <gh-pgvector-pgvector-1058@github.com>
Thanks @Waterpine, I'm currently working on getting a version of this merged. It looks like the on-disk tuple sort is efficient with little memory, so I think we can use most of `work_mem` for the binary heap.