发表机构
University of Cambridge; University of Oxford; Quettaflop AI（剑桥大学; 牛津大学; Quettaflop AI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文搭建了二手GPU组成的DumpsterCluster，可在60美元级GPU上支撑LLaMA-70B推理，经济优势显著，但需结合低价电力与清洁能源以保障可持续性。
AI 中文摘要
随着AI数据中心淘汰功能正常的GPU，大量仍具备算力的加速器流入二手市场。本文探究这些退役GPU能否通过改造形成DumpsterCluster，以支撑现代大语言模型（LLM）推理，以及这种再利用在何种条件下具备经济可行性与环境可持续性。我们从零开始仅使用二手组件搭建了一个128-GPU的DumpsterCluster并运行了一年。按当前市场价格计算，该DumpsterCluster成本为2.2万美元，而一套8-GPU的B200系统成本为60万美元，经济优势显著。通过流水线并行优化，基于V100的DumpsterCluster实现了与LLaMA-70B相当的吞吐量，验证了其生产可行性。但部署过程中也发现了关键的上下文依赖问题：老旧GPU每处理一个token的能耗显著更高，因此总拥有成本仅在电价低廉的地区才具备优势。按电网平均碳强度计算，二手系统处理每个token的总碳排放量，对于8B模型约为当前新一代硬件的4倍，对于70B模型则超过40倍。这些发现表明，GPU的“后生命周期”并非在所有场景下都具备可持续性，硬件再利用必须与低碳能源源战略结合。在能源经济条件有利且电力清洁的地区部署时，二手GPU为扩大AI算力、同时提升可负担性、能源安全与环境责任提供了可行路径。
英文摘要
As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets. This paper investigates whether these retired GPUs can find a productive afterlife to form a DumpsterCluster that can serve modern LLM inference, and under what conditions such repurposing is economically viable and environmentally sustainable. We physically built a 128-GPU DumpsterCluster from scratch using only second-hand components and ran it for one year. At current market prices (\$22K for the DumpsterCluster vs. \$600K for an 8-GPU B200 system), the economic advantages are substantial. Through pipeline-parallel optimizations, our V100 based DumpsterCluster achieves competitive LLaMA-70B throughput, validating production viability. However, our deployment reveals critical context dependencies. Older GPUs consume significantly more energy per token, making total cost of ownership favorable only in regions with inexpensive electricity. Under grid-average carbon intensity, second-hand systems can produce approximately 4x higher total carbon emissions per token for 8B models, and over 40x for 70B models, compared to current-generation hardware. These findings show that GPU afterlife is not universally sustainable - hardware repurposing must be strategically coupled with low carbon energy sources. When deployed in regions with favourable energy economics and clean electricity, second-hand GPUs offer a viable pathway for expanding AI capacity while advancing affordability, energy security, and environmental responsibility.
