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

arXiv: https://arxiv.org/abs/2505.23970 · HTML: https://mlsanity.com/paper/2505.23970/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 29 May 2025.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 5 of 5)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions](https://mlsanity.com/paper/2412.20322/) (2024)
- [The Dirty Secret of SSDs: Embodied Carbon](https://mlsanity.com/paper/2207.10793/) (2022)
- [EnsembleCI: Ensemble Learning for Carbon Intensity Forecasting](https://mlsanity.com/paper/2505.01959/) (2025)

## Built on by (most cited first, 1 of 1)

- [Beyond Energy: When Sustainability Dimensions Reshape LLM Serving Decisions](https://mlsanity.com/paper/2609.35569/) (2026)

## Abstract (arXiv)

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.