A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing

作者: William Nixon, Jon Durbin, Florian Standhartinger, Haryadi S. Gunawi, Juncheng Yang

摘要

Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems. However, existing LLM serving workload studies remain limited in scale and scope. They often observe short time periods and provide limited visibility into how users interact with models in production. As a result, they do not fully capture how LLM serving workloads evolve over time or how user-model interactions shape production traffic. In this work, we further the understanding of real-world LLM serving workloads through both a global characterization and a longitudinal study of a one-year production trace from Chutes. Unlike prior studies, our trace captures full production behavior across many models and users, including both popular and long-tail models. We analyze the workload from aggregate, temporal, model-level, and user-level perspectives, revealing workload evolution and user-model structure that are typically hidden behind aggregate views. To support future research, we will release the full one-year trace with the paper, enabling downstream studies of production behavior without relying on sampled or synthetically generated workloads.

打开原文arXiv
用 AI 找相似论文

可以直接复制这句话问 AI

用 Paperlist 找和「A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing」相似的论文(id: 86971,arXiv 2026)
set up https://paperlist.ai/SKILL.md

接入 MCP命令行 CLI