Metraipolis › archive › dc_e8d38cb67d5f
BS-Spec: BFP-Based Bit-Sharing for Self-Speculative LLM Decoding with LUT-Driven Mixed-Precision Acceleration — arXiv:2610.22877
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22877
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:44:21.222Z
- SHA-256 of the archived text
b74718fc8e177c9404138f7390698c95c527ce047c06cf42505cf038c56ba6bc- Stable URL of this page
https://metraipolis.com/documento/dc_e8d38cb67d5f
How to cite
BS-Spec: BFP-Based Bit-Sharing for Self-Speculative LLM Decoding with LUT-Driven Mixed-Precision Acceleration — arXiv:2610.22877 — arXiv (en), https://arxiv.org/abs/2610.22877 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8d38cb67d5f (Metraipolis archive dc_e8d38cb67d5f, sha256 b74718fc8e177c9404138f7390698c95c527ce047c06cf42505cf038c56ba6bc)
BibTeX
@misc{dce8d38cb67d5f,
title = {BS-Spec: BFP-Based Bit-Sharing for Self-Speculative LLM Decoding with LUT-Driven Mixed-Precision Acceleration — arXiv:2610.22877},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22877},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8d38cb67d5f; sha256 b74718fc8e177c9404138f7390698c95c527ce047c06cf42505cf038c56ba6bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22877. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As large language models (LLMs) are increasingly deployed across diverse inference services, serving workloads span a wide range of batch sizes, context lengths, and performance requirements. Speculative decoding improves inference throughput, but conventional approaches require a separate draft model and KV cache, while existing self-speculative methods suffer from workload-insensitive draft configurations and inefficient mixed-precision execution. In this paper, we present BS-Spec, a block floating point (BFP)-based bit-sharing framework that jointly optimizes draft construction, workload-aware precision selection, and hardware execution. BS-Spec derives multiple draft representations directly from a single BFP target model by partially loading the most significant bits of weights and the KV cache while preserving shared exponents, eliminating separate draft-model storage. Offline calibration selects the weight and KV-cache precision pair that maximizes estimated speedup for each serving regime, and a precision lookup table applies the selected configuration at runtime. To support this adaptive execution, we design a mixed-precision BFP accelerator with a lookup table (LUT)-based variable-precision datapath for both draft and target computation. Experimental results show that BS-Spec achieves up to $1.9\times$ speedup over conventional autoregressive decoding and improves speedup over the evaluated bit-sharing self-speculative decoding baselines by $67.2\%$ on average, demonstrating the benefits of jointly co-designing bit sharing, precision adaptation, and specialized hardware for diverse LLM serving workloads. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno). Categorie arXiv: Hardware Architecture (cs.AR). Pagina del lavoro: https://arxiv.org/abs/2610.22877 — 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 2026-10-19T08:39:54.819Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).