Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving

[2505.23970] Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Distributed, Parallel, and Cluster Computing arXiv:2505.23970 (cs) [Submitted on 29 May 2025 ( v1 ), last revised 11 Apr 2026 (this version, v3)] Title: Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving Authors: Yuyang Tian , Desen Sun , Yi Ding , Sihang Liu View a PDF of the paper titled Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving, by Yuyang Tian and Desen Sun and Yi Ding and Sihang Liu View PDF HTML (experimental) Abstract: 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. Subjects: Distributed, Parallel, and Cluster Computing (cs.DC) ; Hardware Architecture (cs.AR) Cite as: arXiv:2505.23970 [cs.DC] (or arXiv:2505.23970v3 [cs.DC] for this version) https://doi.org/10.48550/arXiv.2505.23970 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yuyang Tian [ view email ] [v1] Thu, 29 May 2025 19:52:44 UTC (533 KB) [v2] Mon, 19 Jan 2026 05:40:03 UTC (570 KB) [v3] Sat, 11 Apr 2026 06:24:23 UTC (573 KB) Full-text links: Access Paper: View a PDF of the paper titled Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving, by Yuyang Tian and Desen Sun and Yi Ding and Sihang Liu View PDF HTML (experimental) TeX Source view license Current browse context: cs.DC < prev | next > new | recent | 2025-05 Change to browse by: cs cs.AR References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Watermarkable Multi-Draft Speculative Sampling via Poisson Processes#1036247
• Watermarkable Multi-Draft Speculative Sampling via Poisson Processes#1006782
• The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference#1084260
• MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation#798916
• MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation#797502