KV-Repurpose is an open‑source, vLLM‑based system that enables segment‑wise KV‑cache reuse beyond exact prompt prefixes in large language model serving. It integrates cache‑aware segment scheduling, prompt construction, capacity management, workload generation, and runtime monitoring. Experiments show that while naive segment reuse maintains output quality for single‑document tasks, it reveals limitations in cross‑document reasoning, and under a Zipfian RAG‑style workload it achieves a 63.9% token‑level cache hit rate versus 3.3% for prefix caching at 30 GB, dramatically lowering time‑to‑first‑token.
arXiv:2607. 05399v1 Announce Type: cross Abstract: Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks.
By Nikita Agrawal, Ruben Mayer
arXiv:2607. 28069v2 Announce Type: replace Abstract: Long-context retrieval and agentic workloads repeatedly reuse the same documents under changing instructions, histories, and document orders.
By Hui Xie, Peng Xiao, Yutong Deng, Shuoran Dou, Jian Yang, Jinyang Guo
The paper discusses position‑independent KV cache reuse, a technique designed to cut latency in retrieval‑augmented generation by reusing chunk‑level KV caches across prompts. It argues that current evaluation methods overstate the accuracy of such reuse because they do not accurately capture the loss of accuracy, and that existing datasets lack the necessary reuse dynamics for thorough testing. To remedy this, the authors propose a new evaluation methodology that unambiguously measures accuracy loss and introduce Boxoffice, a tool that programmatically creates datasets with challenging KV cache reuse patterns.
By Samuel Cestola, Tianxiang Xia, Pengfei Zheng, Weiyan Zheng, Bo Wang, Yi Zhao, Diego Didona
The paper addresses the challenge of long input contexts in Retrieval-Augmented Generation (RAG) systems, where concatenating many retrieved chunks increases prefill workload and time to first token (TTFT). It proposes a dual strategy: fine‑tuning the model to be aware of KV cache concatenation and selectively recomputing only part of the KV caches. Experiments on the RULER benchmark show that for a 124k‑token input, this combined method boosts the RULER score by 9.7 points over a baseline that recomputes caches only, while cutting TTFT by 80% compared with full attention.
By Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi
arXiv:2608.21362v1 Announce Type: new
Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing...
By Srihari Unnikrishnan