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

• URL: http://arxiv.org/abs/2609.09768v1
• Date: Wed, 09 Sep 2026 06:12:39 GMT
• Title: Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?
• Abstract summary: In Retrieval-Augmented Generation (RAG) systems, a large number of retrieved chunks are retrieved to form the input context.<n>As a result, the input context length increases substantially, leading to a larger prefill workload.<n>We propose a combined approach that fine-tunes the model while taking KV cache concatenation into account and selectively recomputes a subset of the KV caches.
• Score: 2.381405202108335
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration [67.17709877327232]
  Cate KV is a hybrid KV cache method that retains only critical token information for consistent heads.<n>Cate KV reduces memory usage by up to $2.72times$ and accelerates decoding by $2.18times$ in single-sample inputs.
  arXiv  Detail & Related papers  (2026-08-31T06:02:37Z)
• MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering [75.0394545769057]
  KV-caching stores the Key-Value of the historical tokens via LLM prefill.<n>MuKV is a method that features a multi-grained KV cache compression module and a semi-hierarchical retrieval approach.<n> Experiments on long-streaming VideoQA benchmarks show that MuKV significantly improves answer accuracy, without sacrificing memory and online QA efficiency.
  arXiv  Detail & Related papers  (2026-05-21T10:13:03Z)
• RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache [28.54642982960947]
  Large language models (LLMs) have shown strong performance across diverse tasks, but their inference with long input contexts is bottlenecked by memory size and bandwidth.<n>Existing methods reduce the cache by either eviction or quantization, but typically treat the two in isolation.<n>In this paper, we cast KV cache compression as a rate-distortion problem, under which eviction and quantization are two end-points of the same bit allocation scheme.
  arXiv  Detail & Related papers  (2026-05-08T15:15:06Z)
• ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation [22.835149054167122]
  We propose Prophet KV, a user-query-driven KV Cache reuse method for RAG scenarios.<n> Prophet KV prioritizes tokens based on their semantic relevance to the user query.<n>Our evaluation results show that Prophet KV retains 96%-101% of full-prefill accuracy with only a 20% recomputation ratio.
  arXiv  Detail & Related papers  (2026-01-31T09:53:31Z)
• Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction [53.83828564664595]
  Large language models (LLMs) utilize key-value ( KV) cache to store historical information during sequence processing.<n>Current methods for KV cache eviction typically utilize the last window from the pre-filling phase as queries to compute the KV importance scores for eviction.<n>We propose Judge Q, a novel training method which incorporates a soft token list.
  arXiv  Detail & Related papers  (2025-09-13T03:34:12Z)
• Sparse Attention across Multiple-context KV Cache [8.236266965773465]
  Reusing historical Key-Value ( KV) Cache for improved inference efficiency has become a mainstream approach.<n>Recent advances further enhance throughput by sparse attention mechanisms to select the most relevant KV Cache.<n>This paper presents SamKV, the first exploration of attention sparsification for multiple-context KV Cache.
  arXiv  Detail & Related papers  (2025-08-06T02:53:14Z)
• FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression [18.12657364501536]
  FAEDKV is a novel, training-free KV cache compression framework.<n>It preserves both early and recent contextual information.<n>Experiments on LongBench benchmark demonstrate FAEDKV's superiority over existing methods by up to 22%.
  arXiv  Detail & Related papers  (2025-07-26T18:20:25Z)
• KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding [72.12756830560217]
  Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI.<n>Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value cache during inference has emerged as a primary efficiency bottleneck.<n>By down-sampling the Key-Value vector dimensions into a latent space, we can significantly reduce the KV Cache footprint and improve inference speed.
  arXiv  Detail & Related papers  (2025-07-15T12:52:12Z)
• Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs? [79.58770714228983]
  Language models handle increasingly long contexts for tasks such as book summarization.<n>This leads to growing memory costs for the key-value ( KV) cache.<n>Many prior works have proposed ways of discarding KVs from memory, but their approaches are tailored to favorable settings.<n>We propose the * KV footprint* as a unified metric, which accounts for both the amount of KV entries stored and their lifespan in memory.
  arXiv  Detail & Related papers  (2025-06-20T16:21:12Z)
• More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression [71.42818367729573]
  In large language models (LLMs), the memory usage of KV cache has become a critical bottleneck during inference.<n>The mainstream KV compression methods, including KV pruning and KV quantization, primarily focus on either token or precision dimension separately.<n>In this paper, we comprehensively investigate the token-precision trade-off in KV cache compression.
  arXiv  Detail & Related papers  (2024-12-17T09:20:31Z)
• SCBench: A KV Cache-Centric Analysis of Long-Context Methods [61.025422435235456]
  We introduce SCBench, a benchmark for evaluating long-context methods from a KV cachecentric perspective.<n>We provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs and Mamba-Attention hybrids.<n>Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n2) pre-filling perform robustly.
  arXiv  Detail & Related papers  (2024-12-13T17:59:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.