aceModerate evidence
Published recordClimateGood Space
More
Cache Your Prompt When It's Green - Carbon-aware Caching for Large Language Model Serving
- Truvace record
- TRV-2026-2628raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Benchmark or lab evaluation
- Sources
- 1 sourcePeer-reviewed
- sha256
- 63a2c9559a8e…check it
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 ca…
The gain
In tests replaying real request and grid traces, GreenCache cut average carbon emissions of serving Llama-3 70B by 15.1% on France's grid, up to 25.3%, versus a full-size cache, while keeping over 90% of requests within latency targets.
What this doesn’t fix
The evaluation used simulated one-day traces on a single four-GPU server with a 16 TB SSD cap, scaled-down Azure request rates and one date's carbon intensity, so real production savings may differ.
Sources
1 on file- ACM SIGMETRICS Performance Evaluation Reviewdoi:10.1145/3820171.3806850
Cite this record
v1Truvace Impact Record TRV-2026-2628, v1: “Cache Your Prompt When It's Green - Carbon-aware Caching for Large Language Model Serving.” Truvace, 2026-11-12. /record/TRV-2026-2628 (accessed on the day you copy it). sha256 63a2c9559a8eed63…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2628 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.