4 papers · 1 filter
Beyond Energy: When Sustainability Dimensions Reshape LLM Serving Decisions
Tianyao Shi, Xipeng Shen, Yi Ding
Large language model (LLM) serving has environmental impacts across energy consumption, carbon emission, water consumption, and biodiversity loss. Yet these dimensions are largely…
BrownoutMoE: Structure-Aware Expert Grouping for Efficient and Accurate LLM Web-based Services
Yi Ding, Minxian Xu, Zhengxin Fang +2
Mixture-of-Experts (MoE) large language models (LLMs) are increasingly deployed in Web-facing services, where inference must be both accurate and responsive under bursty demand. Al…
TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent Systems
Yi Ding, Zijie Xuan, Haowei Zhou +6
Effective multi-agent systems cannot be designed by selecting prompts or communication graphs in isolation. Agent behavior depends on the information an agent receives, while the u…
BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving
Tianyao Shi, Yi Ding
Large language model (LLM) serving creates environmental impacts beyond carbon and water, including ecosystem damage through biodiversity-related pathways. We present BIRDS, a fram…