2026· Annual Meeting of the Association for Computational Linguistics· pp. 18861-18871· 1 citation· 28 references
Computer Science
TL;DR
This work finds that the deep-layer features of a lightweight speculative model exhibit strong consistency with the target model in the selection of critical tokens for recomputation, and proposes SpecCache, which employs deep-layer hidden-state norms from a speculative model as a proxy to guide the critical token selection for target large model.
Abstract
Retrieval-Augmented Generation (RAG) significantly enhances LLMs but faces high prefill latency during long-context processing. While KV cache reuse can mitigate this, current meth-ods relying on shallow features or static heuristics often fail to identify critical tokens for recomputation, resulting in generation quality degradation. We have an insight that KV deviations are more pronounced in deep layers. However, directly extracting deep-layer features from the target model is computationally prohibitive. Crucially, we find that the deep-layer features of a lightweight speculative model exhibit strong consistency with the target model in the selection of critical tokens for recomputation. In light of these insights, we propose SpecCache, which employs deep-layer hidden-state norms from a speculative model as a proxy to guide the critical token selection for target large model. Experiments demonstrate that SpecCache outperforms state-of-the-art (SOTA) baselines. Compared to full KV recomputation, it reduces time-to-first-token (TTFT) by 2 . 17 − 3 . 95 × and increases inference throughput by 2 . 7 − 5 . 2 × , with negligible degradation in generation quality relative to full recomputation.
A novel method, namely AnDPro, is proposed, which introduces a projection-based scoring function to more accurately measure token importance and guide more accurate token selection in key-Value cache eviction.
Zijie Geng, Jie Wang, Ziqi Liu et al.· Neural Information Processin...· 6 citations
This work proposes DistillCache, a reinforcement learning framework that formulates KV-cache eviction as a sequential decision problem and demonstrates the effectiveness of learned, distribution-aware policies for memory-efficient long-context LLM inference.
Modern large language model (LLM) inference suffers from severe Time-To-First-Token (TTFT) bottlenecks. Existing prefix KV caching mechanisms are inherently stateless, forcing a trade-off between cross-chunk attention accuracy and online recomputation overhead. To address this issue, we propose Pegasus, a novel stateful prefix KV caching system that aims to achieve full-context attention accuracy while avoiding costly recomputation. To handle the exponential growth of context states under limited memory capacity, Pegasus employs a Recursive Path-Pruning Caching (RPPC) algorithm to selectively cache high-value states based on access frequency, memory footprint, and asymmetric latency benefit. In addition, Pegasus introduces a transition-based KV management mechanism to mitigate cache-miss overhead. By exploiting the sparsity of state-dependent KV variations, it replaces expensive attention recomputation and I/O-intensive tensor reloading with lightweight sparse state transitions. Extensive experiments show that Pegasus improves end-to-end serving throughput by 45.9% on average, reduces TTFT by up to 78.5%, and lowers cache-miss recovery overhead by more than 72%.
Fahao Chen, Peng Li, Dongxiao Yu et al.· Fall Joint Computer Conferen...· 0 citations
Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation. To mitigate the growing inference cost, recent work has explored non-prefix key-value (KV) cache reuse to reduce redundant prefill computation. However, existing reuse methods primarily focus on computation savings and overlook a critical bottleneck in long-context LLM serving: the cost of storing and accessing large KV caches. While KV compression appears to be a natural complement, naively combining compression with non-prefix KV reuse often leads to severe accuracy degradation. In this work, we propose C2KV, a unified framework for non-prefix KV reuse that jointly optimizes KV cache compression and concatenation. C2KV learns a composable and compressed KV cache manifold that is explicitly designed to be position-agnostic. Our approach introduces a lightweight sidecar Extractor with learnable compression tokens and a structured attention flow, enabling modular KV representations that can be flexibly reused and concatenated without modifying the frozen base model. We further employ a compression-concatenation co-training strategy to align extraction-time representations with their downstream reuse behavior. Extensive experiments across multiple long-context benchmarks and model families demonstrate that C2KV significantly reduces KV cache storage and transfer costs, achieving up to 17× inference speedup under long contexts, while preserving generation quality.
Chuheng Du, Junyi Chen, Hanlin Tang et al.· Proceedings of the 32nd ACM...· 1 citation
LLM serving is increasingly accelerated by position-independent caching (PIC). Existing PIC methods, however, are built for full-attention models, where a token-indexed KV cache underlies its core operations: matching reusable token chunks, concatenating their KV entries, and selectively recomputing a few tokens to restore cross-chunk context. Hybrid LLMs break these primitives---they replace most attention layers with linear recurrences that expose only a fixed-size state, leaving no token-indexed KV to concatenate or to locally repair. This raises a natural question: can PIC benefit hybrid models, and what would it take? We present LinearKV, a training-free hybrid-PIC framework. Its key insight is a \emph{decoupled initialization}: each linear layer maps its $K$ matched local states to a single initial state, while full-attention layers concatenate their KV as before. LinearKV is therefore compatible with existing PIC methods, reusing their token selection and recomputation as-is. Under this framework, we find that a \emph{single cached state} suffices as the linear layer's initializer. The algebraically principled alternative---composing all $K$ cached states into the exact full-prefix state, as concurrent work HYPIC does---is unnecessary and, on some architectures, even harmful. We compare the two across three hybrid models and three PIC selectors. On the two GDN models the two tie, both recovering most of full quality (up to $92\%$); on the Mamba-2 model, exact composition instead collapses under every selector---under EPIC, for instance, it recovers only $46.6\%$ of full quality, versus $86.8\%$ for a single cached block initializer. A single state initializer is also cheaper, cutting time-to-first-token to $0.46\times$ full prefill versus a further $5$--$17\%$ overhead for exact composition; results hold across LongBench QA and RULER at 8K--32K.
Yi-Rui Liu, Ruoling Qi, Long-Wen Wang et al.· 1 citation
Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets. Existing methods primarily improve which original KV pairs are retained. We introduce RestoreKV, which complements this selection-based formulation with learned restoration under the same total KV budget. Our key insight is that, although the information lost through eviction is context-specific, the mechanism for generating its compact complement can be shared across contexts. After context prefill, a few restore tokens attend to the full KV cache in a single LoRA-adapted pass, generating a compact, context-conditioned restore cache. The base importance scorer and eviction rule remain unchanged, and the adapters are disabled for all subsequent queries and decoding. RestoreKV is trained through parameter-efficient self-distillation from the frozen full-cache model, optimizing only $0.4\%$ of the parameters and requiring no task-specific tuning. Across four backbones and four long-context benchmarks, RestoreKV substantially reduces compression-induced degradation. On Qwen3-4B, it improves 59 of 60 paired, budget-matched settings across five base eviction methods; at a $5\%$ budget, it raises KVzip from $38.2$ to $73.2$ on RULER-4K. Applied to KVzip+, RestoreKV reaches $86.4$ RULER accuracy at $16\times$ compression on the KVPress Benchmark, while adding less than $0.5\%$ one-time cache-construction overhead in a 32K-context evaluation. Our project page is available at https://paper.pnu-cvsp.com/RestoreKV/
