Metraipolis › archive › dc_2fc596f78a5c

VQ-bench: A Composable Vector Quantization Framework — arXiv:2608.11240

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11240
License (as archived)
CC0-1.0
Archived
2026-10-19T05:15:14.575Z
SHA-256 of the archived text
a2590662db2addc54dd905b4050de7229c21030ae22ff8a3b2a61d8259fda86f
Stable URL of this page
https://metraipolis.com/documento/dc_2fc596f78a5c

How to cite

VQ-bench: A Composable Vector Quantization Framework — arXiv:2608.11240 — arXiv (en), https://arxiv.org/abs/2608.11240 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fc596f78a5c (Metraipolis archive dc_2fc596f78a5c, sha256 a2590662db2addc54dd905b4050de7229c21030ae22ff8a3b2a61d8259fda86f)
BibTeX
@misc{dc2fc596f78a5c,
  title = {VQ-bench: A Composable Vector Quantization Framework — arXiv:2608.11240},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11240},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fc596f78a5c; sha256 a2590662db2addc54dd905b4050de7229c21030ae22ff8a3b2a61d8259fda86f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11240. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vector quantization is an old problem but has recently become central to AI infrastructure. It is therefore experiencing a surge of renewed engineering and research activity. This paper provides a unified framework for developing and benchmarking new quantization algorithms. We describe 7 common conceptual quantization primitives and show how to compose them arbitrarily. We then re-express 25 common quantizers as pipelines of these primitives. Finally, we publish VQ-bench as open-source to be extended further and make reproducible benchmarks publicly available.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.11240 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:08:46.609Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).