Jiakun Fan

Jiakun Fan

Auto-generated profile, based on publicly available information

Jiakun Fan

Virginia Tech, Blacksburg, Virginia, USA

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 December 2025
Verified
Conference Paper
Open access
XLXiangchen Li
Xiangchen Li
DSDimitrios Spatharakis
Dimitrios Spatharakis
SGSaeid Ghafouri
Saeid Ghafouri
JFJiakun Fan
Jiakun Fan
HVHans Vandierendonck
Hans Vandierendonck
DNDimitrios Nikolopoulos
Dimitrios Nikolopoulos


29 May 2026 in Proceedings of the ACM on Measurement and Analysis of Computing Systems
Verified
Journal Article
Open access
XLXiangchen Li
Xiangchen Li
JFJiakun Fan
Jiakun Fan
QWQingyuan Wang
Qingyuan Wang
DSDimitrios Spatharakis
Dimitrios Spatharakis
SGSaeid Ghafouri
Saeid Ghafouri
DNDimitrios Nikolopoulos
Dimitrios Nikolopoulos
As Large Language Models (LLMs) become increasingly accessible to end users, an ever-growing number of inference requests are initiated from edge devices and computed on centralized GPU clusters. However, the resulting exponential growth in computation workload is placing significant strain on data centers, while edge devices remain largely underutilized, leading to imbalanced workloads and resource inefficiency across the network. Integrating edge devices into the LLM inference process via speculative decoding helps balance the workload between the edge and the cloud, while maintaining lossless prediction accuracy. In this paper, we identify and formalize two critical bottlenecks that limit the efficiency and scalability of distributed speculative LLM serving: Wasted Drafting Time and Verification Interference. To address these challenges, we propose WISP , an efficient and SLO-aware distributed LLM inference system that consists of an intelligent speculation controller, a verification time estimator, and a verification batch scheduler. These components collaboratively enhance drafting efficiency and optimize verification request scheduling on the server. Extensive numerical results show that WISP improves system capacity by up to 2.1× and 4.1×, and increases system goodput by up to 1.94× and 3.7×, compared to centralized serving and SLED , respectively.

5 July 2026
Verified
Conference Paper
Open access
JFJiakun Fan
Jiakun Fan
YZYanglin Zhang
Yanglin Zhang
XLXiangchen Li
Xiangchen Li
DNDimitrios Nikolopoulos
Dimitrios Nikolopoulos

26 April 2026
Verified
Conference Paper
Open access
XLXiangchen Li
Xiangchen Li
SGSaeid Ghafouri
Saeid Ghafouri
JFJiakun Fan
Jiakun Fan
BABabar Ali
Babar Ali
HVHans Vandierendonck
Hans Vandierendonck
DNDimitrios Nikolopoulos
Dimitrios Nikolopoulos
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 configuration-selection 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 efficiency across the joint configuration space. Our analysis across three edge platforms and two LLM families reveals structurally conflicting optima. Firstly, goodput is maximised by the smallest, fastest draft model at device-dependent speculative lengths (K* =2-10). Secondly, both cost and energy efficiency converge to K=2 due to a dominant bonus-token effect—with cost favouring the largest drafter for its high acceptance rate and energy favouring the smallest for its low power draw. These conflicts confirm that no single fixed configuration can simultaneously optimise all objectives, underscoring the need for profiling-based configuration selection in disaggregated edge-cloud LLM inference.

20 July 2026 in ACM SIGMETRICS Performance Evaluation Review
Verified
Journal Article
Open access
XLXiangchen Li
Xiangchen Li
JFJiakun Fan
Jiakun Fan
QWQingyuan Wang
Qingyuan Wang
DSDimitrios Spatharakis
Dimitrios Spatharakis
SGSaeid Ghafouri
Saeid Ghafouri
DNDimitrios Nikolopoulos
Dimitrios Nikolopoulos
LLM inference is increasingly initiated at edge devices but still executed in centralized GPU clusters. Distributed speculative edge serving offloads drafting to devices, yet existing systems scale poorly under heterogeneous, latency-sensitive workloads. We identify two bottlenecks: Wasted Drafting Time (WDT), where devices over-draft tokens later rejected by the verifier, and Verification Interference , where long verifications delay short requests within a micro-batch. We present WISP , a lossless distributed speculative serving system that combines dynamic drafting with SLO-aware verification batching. WISP uses a lightweight rejection predictor, a batch-latency estimator, and an interference-aware scheduler. Across simulation and prototype experiments, WISP improves system capacity by up to 2.1× over centralized serving and 4.1× over SLED , and improves system goodput by up to 1.94× and 3.7×, while reducing token-speed SLO violations under bursty multi-tenant workloads.