paper-with-me

홈 › Papers

Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?

2026-09-09 · Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi arxiv

In Retrieval-Augmented Generation (RAG) systems, a large number of retrieved chunks are concatenated to form the input context so that users can receive high-quality responses based on external knowledge. As a result, the input context length increases substantially, leading to a larger prefill workload and, in turn, a longer time to first token (TTFT). While previous works that reuse precomputed key-value (KV) caches effectively reduce TTFT for long-context inputs, it remains unclear whether response quality is preserved when the input context becomes very long. In this paper, we propose a combined approach that (i) fine-tunes the model while taking KV cache concatenation into account and (ii) selectively recomputes a subset of the KV caches. By applying both techniques, we demonstrate improved accuracy for long-context inputs. Experiments on the RULER benchmark show that, for a 124k-token input, our method improves the RULER score by 9.7 point over the baseline that recomputes KV caches only. Moreover, TTFT is reduced by 80% compared with full attention.

📄 PDF Abstract BibTeX arXiv:2609.09768

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse

2025-02-21 · Jingbo Yang, Bairu Hou, Wei Wei, Yujia Bao 외

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appe…

Question Answering

Activated LoRA: Fine-tuned LLMs for Intrinsics

2025-04-16 · Kristjan Greenewald, Luis Lastras, Thomas Parnell, Vraj Shah 외

Low-Rank Adaptation (LoRA) has emerged as a highly efficient framework for finetuning the weights of large foundation models, and has become the go-to method for data-driven customization of LLMs. Despite the promise of …

The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference

2026-03-20 · Kaleem Ullah Qasim, Jiashu Zhang, Muhammad Kafeel Shaheen, Razan Alharith 외 arxiv

The key-value (KV) cache is widely treated as essential state in transformer inference, and a large body of work engineers policies to compress, evict, or approximate its entries. We prove that this state is entirely red…

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs

2026-04-14 · Chuangtao Chen, Grace Li Zhang, Xunzhao Yin, Cheng Zhuo 외 arxiv

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV sta…

QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving

2026-06-04 · Jianxin Yan, Wangze Ni, Zhenxin Li, Jiabao Jin 외 arxiv

Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost. RAG…