Metraipolis › archive › dc_fdb97faf8ce9
FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy — arXiv:2608.15602
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15602
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:03:50.382Z
- SHA-256 of the archived text
a8c095cd6cc8911ade75c9a0aef12af4711bb835bbfa78bb2395de24f0e7a4e2- Stable URL of this page
https://metraipolis.com/documento/dc_fdb97faf8ce9
How to cite
FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy — arXiv:2608.15602 — arXiv (en), https://arxiv.org/abs/2608.15602 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fdb97faf8ce9 (Metraipolis archive dc_fdb97faf8ce9, sha256 a8c095cd6cc8911ade75c9a0aef12af4711bb835bbfa78bb2395de24f0e7a4e2)
BibTeX
@misc{dcfdb97faf8ce9,
title = {FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy — arXiv:2608.15602},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15602},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fdb97faf8ce9; sha256 a8c095cd6cc8911ade75c9a0aef12af4711bb835bbfa78bb2395de24f0e7a4e2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15602. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads. To bridge this gap, we propose FluxBin (\textbf{F}lexible \textbf{L}UT-based \textbf{U}ltra-low-bit e\textbf{X}ecution with \textbf{Bin}ary bases), an algorithm-kernel co-design that synergizes post-training quantization with a highly optimized CUDA kernel. Algorithmically, we introduce Decoupled Row-Column Binary Decomposition to enhance representational capacity while maintaining hardware efficiency, complemented by a Hessian-guided saliency-aware hybrid bases that preserve critical information. At the kernel level, we implement a Lookup Table Building Approach with Scale Fusion to reduce floating-point arithmetic, featuring a Virtual Columnar Mapping that transforms irregular, sparse, and salient matrices into dense execution. Extensive evaluations demonstrate FluxBin achieves up to $5.92\times$ speedup and $10.19\times$ energy savings across diverse model architectures, delivering comparable accuracy to heavily fine-tuned methods. This effectively enables the deployment of 70B-scale models on one single A100 GPU with a $4\times$ memory reduction. Code is available at this https URL .
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15602 — 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 2026-10-18T16:29:14.030Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).