WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching
Published:
Recommended citation: Li, X., Fan, J., Wang, Q., Spatharakis, D., Ghafouri, S., Vandierendonck, H., John, D., Butt, A.R., & Nikolopoulos, D.S. (2026). *WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching*. arXiv:2601.11652 [cs.CV].
Download Paper