5 papers
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 +7
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 centralize…
Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices
Saeid Ghafouri, Mohsen Fayyaz, Xiangchen Li +4
Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label…
SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving
Xiangchen Li, Dimitrios Spatharakis, Saeid Ghafouri +5
The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-devic…
QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference
Xiangchen Li, Saeid Ghafouri, Bo Ji +3
As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of…
HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models
Kazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S. Nikolopoulos +3
High-resolution Vision-Language Models (VLMs) are widely used in multimodal tasks to enhance accuracy by preserving detailed image information. However, these models often generate…