Metraipolis › archive › dc_eb4efd57eeca

AutoQS: Automated Quantization Strategy Design with Large Language Models — arXiv:2611.11975

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.11975
License (as archived): CC0-1.0
Archived: 2026-11-10T18:41:39.875Z
SHA-256 of the archived text: f7a7bc27d81888df4cd87e372b44b1c56fe9f97cc06173e0f068268b842408cf
Stable URL of this page: https://metraipolis.com/documento/dc_eb4efd57eeca

How to cite

AutoQS: Automated Quantization Strategy Design with Large Language Models — arXiv:2611.11975 — arXiv (en), https://arxiv.org/abs/2611.11975 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb4efd57eeca (Metraipolis archive dc_eb4efd57eeca, sha256 f7a7bc27d81888df4cd87e372b44b1c56fe9f97cc06173e0f068268b842408cf)

BibTeX

@misc{dceb4efd57eeca,
  title = {AutoQS: Automated Quantization Strategy Design with Large Language Models — arXiv:2611.11975},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11975},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb4efd57eeca; sha256 f7a7bc27d81888df4cd87e372b44b1c56fe9f97cc06173e0f068268b842408cf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11975. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quantization reduces LLM deployment costs, but effective strategies must balance model quality and storage. LLM-driven search can automate strategy design through repeated proposal and evaluation. This process must identify useful strategies within a limited evaluation budget. The key challenge is that \textit{actual quantization is expensive, while inexpensive proxies may not reflect quantized-model performance.} To address this challenge, we present AutoQS, an \textbf{Auto}mated \textbf{Q}uantization \textbf{S}trategy Design with LLMs. AutoQS keeps weight precision fixed and searches group-size allocations across layers and operators under deployment constraints. Evaluation history guides coordinated LLM proposals, while deterministic validation ensures compatible allocations. An inexpensive quality proxy evaluates candidates, and an candidate repository retains alternative allocations to inform subsequent proposals. Periodic actual quantization complements these proxy evaluations with measured quality and checkpoint storage, providing feedback for further search within the evaluation budget. Experiments on Qwen2.5-7B-Instruct show that AutoQS improves seven-task average accuracy over uniform-group GPTQ and AWQ by 0.70 and 1.12 percentage points, respectively, at four-bit weight precision.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.11975 — 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 2026-11-10T18:37:37.530Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).