As large language models (LLMs) become widely used, their environmental impact, especially carbon emission, has attracted more attention. Prior studies focus on compute-related carbon emissions. In this paper, we find that storage is another key contributor. LLM caching, which saves and reuses KV caches for repeated context, reduces operational carbon by avoiding redundant computation. However, this benefit comes at the cost of embodied carbon from high-capacity, high-speed SSDs. As LLMs scale, the embodied carbon of storage grows significantly. To address this tradeoff, we present GreenCache, a carbon-aware cache management framework that dynamically derives resource allocation plans for LLM serving. GreenCache analyzes the correlation between carbon emission and SLO satisfaction, reconfiguring the resource over time to keep the balance between SLO and carbon emission under dynamic workloads. Evaluations from real traces demonstrate that GreenCache achieves an average carbon reduction of 15.1 % when serving Llama-3 70B in the FR grid, with reductions reaching up to 25.3 %, while staying within latency constraints for > 90 % of requests.

翻译：随着大型语言模型的广泛应用，其环境影响，特别是碳排放问题，日益受到关注。现有研究主要关注计算相关的碳排放。本文发现存储系统是另一关键碳排放源。LLM缓存技术通过保存并复用重复上下文的KV缓存，可避免冗余计算从而降低运营碳排放。然而，这种效益的获取需要以高容量高速固态硬盘带来的隐含碳排放为代价。随着大模型规模扩大，存储系统的隐含碳排放显著增长。为解决这一权衡问题，我们提出GreenCache——一种碳感知缓存管理框架，能够动态制定LLM服务的资源分配方案。GreenCache通过分析碳排放与服务等级协议（SLO）达标率之间的关联，随时间动态重构资源配置，在动态工作负载下维持SLO达标与碳排放的平衡。基于真实轨迹的评估表明，在法国电网区域服务Llama-3 70B模型时，GreenCache在保证90%以上请求满足延迟约束的前提下，平均降低15.1%的碳排放，最高减排幅度可达25.3%。