ConfigSpec: Profiling-Based Configuration Selection for Distributed Edge--Cloud Speculative LLM Serving
Speculative decoding enables collaborative Large Language Model (LLM) inference across cloud and edge by separating lightweight token drafting from heavyweight verification. While prior systems show performance and cost benefits, practical deployment requires navigating a large configuration space spanning draft model variants, quantisation levels, speculative lengths, and heterogeneous edge devices. This paper presents ConfigSpec, a configurationselection framework for distributed speculative LLM serving. ConfigSpec profiles edge devices and draft-target alignment, and models drafting throughput, acceptance rate, and power to evaluate goodput, verification cost efficiency, and energy eff...
| Authors | Xiangchen Li, Saeid Ghafouri, Jiakun Fan et al. |
|---|---|
| Primary category | cs.DC |
| Published | 8 April 2026 |
| Last updated at source | 8 April 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.