collaborators

9 papers

cs.DC2026

FACT: Compositional Kernel Synthesis with a Three-Stage Agentic Workflow

Sina Heidari, Dimitrios S. Nikolopoulos

Deep learning compilers and vendor libraries deliver strong baseline performance but their performance is bounded by finite, engineer-curated catalogs. When these omit needed optim…

cs.SE2026

LLM-Guided Runtime Parameter Optimization for Energy-Efficient Model Inference

Katelyn Crumpacker, Dimitrios Nikolopoulos

Large Language Models (LLMs) have become an integral part of many real-world workflows. However, LLMs consume a lot of energy, which becomes a large concern in the scale of the dem…

cs.DC2026

ConfigSpec: Profiling-Based Configuration Selection for Distributed Edge--Cloud Speculative LLM Serving

Xiangchen Li, Saeid Ghafouri, Jiakun Fan +3

Speculative decoding enables collaborative Large Language Model (LLM) inference across cloud and edge by separating lightweight token drafting from heavyweight verification. While…

cs.DC2026

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…

cs.DC2026

Taming the Memory Footprint Crisis: System Design for Production Diffusion LLM Serving

Jiakun Fan, Yanglin Zhang, Xiangchen Li +1

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. How…

cs.DC2026

APEX: Asynchronous Parallel CPU-GPU Execution for Online LLM Inference on Constrained GPUs

Jiakun Fan, Yanglin Zhang, Xiangchen Li +1

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hy…