Metraipolis › archive › dc_a4e942efe5f3
Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs — arXiv:2608.04048
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04048
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:13:28.807Z
- SHA-256 of the archived text
08ee8c364ad39454c3648d2770adf4ad7ef5975e0fa5e31dbbec85363ee1a520- Stable URL of this page
https://metraipolis.com/documento/dc_a4e942efe5f3
How to cite
Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs — arXiv:2608.04048 — arXiv (en), https://arxiv.org/abs/2608.04048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4e942efe5f3 (Metraipolis archive dc_a4e942efe5f3, sha256 08ee8c364ad39454c3648d2770adf4ad7ef5975e0fa5e31dbbec85363ee1a520)
BibTeX
@misc{dca4e942efe5f3,
title = {Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs — arXiv:2608.04048},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04048},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4e942efe5f3; sha256 08ee8c364ad39454c3648d2770adf4ad7ef5975e0fa5e31dbbec85363ee1a520},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput. However, conventional quantization methods typically require a separate checkpoint for each target bit-width. We introduce Recurrent Residual Quantization (RRQ), a post-training quantization (PTQ) framework that represents weights as a low-bit quantized base together with a sequence of quantized residual corrections, enabling multiple effective precisions from a single checkpoint. Starting from a 2-bit model obtained via post-training quantization (PTQ) or round-to-nearest (RTN), RRQ progressively adds lightweight 2-bit residuals generated via RTN to construct 4-, 6-, and 8-bit representations. The method is calibration-free and avoids joint multi-bit optimization. In our Qwen3-8B setup, the full all-RTN 2-/4-/6-/8-bit package is constructed in 1,293 seconds, 3.3 times faster than the measured MatGPTQ construction. Experiments on six recent LLMs show competitive accuracy at 6 and 8 bits, with model-dependent behavior at 4 bits. The code will be made publicly available upon publication. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.04048 — 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 2026-10-31T11:02:13.469Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).