Metraipolis › archive › dc_eec99c25d469

Intent-Aware Caching for Efficient LLM Serving — arXiv:2611.09715

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09715
License (as archived)
CC0-1.0
Archived
2026-11-09T22:34:14.011Z
SHA-256 of the archived text
6b7c445728eb5abca47a3a41aa13083ef81052fb67ef362e1fa616a22b1a0519
Stable URL of this page
https://metraipolis.com/documento/dc_eec99c25d469

How to cite

Intent-Aware Caching for Efficient LLM Serving — arXiv:2611.09715 — arXiv (en), https://arxiv.org/abs/2611.09715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eec99c25d469 (Metraipolis archive dc_eec99c25d469, sha256 6b7c445728eb5abca47a3a41aa13083ef81052fb67ef362e1fa616a22b1a0519)
BibTeX
@misc{dceec99c25d469,
  title = {Intent-Aware Caching for Efficient LLM Serving — arXiv:2611.09715},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09715},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eec99c25d469; sha256 6b7c445728eb5abca47a3a41aa13083ef81052fb67ef362e1fa616a22b1a0519},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern LLM serving systems use prefix caching to accelerate multi-turn conversational workloads. They cache the key-value states of previous conversation prefixes and reuse them when subsequent requests share the same prefix, to avoid redundant prefill computation and reduce serving latency. However, achieving a high cache hit rate remains challenging because cache reuse depends on whether a conversation continues and how soon the next turn arrives. Our analysis of real workloads shows that user intent is a useful signal for this behavior, as different intents exhibit different continuation probabilities and inter-turn delays. Based on this key insight, we propose Intent-Aware Caching (IAC), an online eviction policy that classifies requests by intent, learns lightweight reuse statistics from recent serving logs and leverages these statistics to guide an oracle-inspired eviction strategy. Extensive evaluation on real workloads (WildChat and ShareChat) shows that IAC reaches a 34.6% cache hit rate. This substantially outperforms both the previous learning-based approach (18.8%) and traditional methods such as least recently used (LRU, 12.2%), while reducing average serving latency by up to 46.1%.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.09715 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:30:47.289Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).