latent.fs / tags / pg_cuvs — 3 items

/feed.xml

TAG

#pg_cuvs

2026-11 3 posts

  1. The Bottleneck Came After the GPU

    Tracing the time CREATE INDEX spends after the GPU has built the graph. On a diagnostic build of GPU-built HNSW, about 49 of 82 seconds went to moving the graph into PostgreSQL pages; in CAGRA, CREATE INDEX took about 15 seconds more than a direct build. This post follows both causes and how much each was reduced (for CAGRA, only in an experimental build so far), with the measurement conditions attached.

    DB #49

  2. Comparing Dissimilar Systems

    Best against best, parameter sweeps, Pareto curves. Lessons on method from comparing pgvector HNSW with pg_cuvs's CAGRA on one million 768-dimensional vectors, and two mistakes in our own setup, each with its conditions.

    DB #48

  3. [PGConf.Asia 2026] A GPU Behind a PostgreSQL Index

    How pg_cuvs is built, what we measured, and what it costs. A written version of my PGConf.Asia 2026 talk, with the comparison against pgvector HNSW at recall 0.99 and its conditions.

    DB #47

TAGS 207

All 207 tags →