WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching.

Xiangchen Li, Jiakun Fan, Qingyuan Wang, Dimitrios Spatharakis, Saeid Ghafouri, Hans Vandierendonck, Deepu John, Bo Ji, Ali Raza Butt, Dimitrios S. Nikolopoulos

Browse the full SIGMETRICS paper archive.