KV Caching

KV: Key-Value

Follow this topic Ask about this topic

Momentum

29 papers in the last four weeks, up 16% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 276

Jul 24, 2026cs.AR

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding

With the rapid adoption of long-context large language models (LLMs), the continuously growing KV cache during decoding has become the critical memory bottleneck. To tackle this challenge, we propose HiKV, a novel algorithm-hardware co-design that exploits KV cache redundancy through hierarchical importance awareness. Algorithmically, HiKV compresses the KV cache at two granularities: Stage I evicts unimportant tokens within a fixed budget, and Stage II further loads only the significant elements of each retained token, reaching compression ratios unattainable at a single granularity. Architecturally, we develop a dedicated accelerator centered on a reconfigurable importance sorter that switches between the distinct sorting datapaths each stage requires, unifying the two-stage acceleration in one circuit with minimal overhead. Evaluated on representative LLMs, HiKV achieves up to 7.95x speedup and 90% energy reduction in the attention computation over the vanilla KV cache baseline within negligible 1% accuracy loss. Under iso-accuracy constraints, HiKV outperforms state-of-the-art importance-based methods by achieving an additional 1.82~4.87x reduction in external memory accesses. These benefits are enabled by specialized hardware components that add only 8% to the system area.

Chao Fang, Jun Yin, Man Shi +1

ESAT-MICAS, KU Leuven, Leuven, Belgium · UC Berkley, CA, USA

KV Caching Memory-Efficient Optimization KV-Cache Eviction LLM Inference Acceleration KV-Cache Compression KV-Cache Pruning

Jul 23, 2026cs.LG

Error Certificates for KV-Cache Eviction via Randomized Design

Deterministic KV-cache eviction keeps the top-

k

tokens under an importance score and deletes the rest. We prove that this design cannot know what it destroyed: evicted values can be altered so that everything the serving system retains is unchanged while the true attention-output error grows arbitrarily, so no serving-time estimator of that error is consistent. Randomized eviction restores identifiability. With a Poisson-sampled tail at known inclusion probabilities, one logit offset performs the Hájek correction inside the softmax, and a survey-sampling variance estimator over the retained set becomes a per-step error certificate with 0.97 empirical coverage at no accuracy cost. On real workloads, seven pre-registered claims locate the certificate's value precisely. Prediction goes to output confidence: question-aware eviction at 25--50% budgets is nearly free, output log-probability predicts failure better than any cache-side signal, and certificate-gated budget escalation adds nothing. Attribution stays with the certificate: it separates cache-induced from inherent failures (AUC 0.65--0.75, against 0.47--0.54 for output confidence) and schedules recomputation better than random or confidence gating. Randomization buys attribution, not prediction.

Peng Xie

Technical University of Munich

KV Caching KV-Cache Eviction

Jul 22, 2026cs.CR

HijackKV: New Threat in Position-Independent KV Cache Reuse

Key-Value (KV) cache reduces inference latency in large language models (LLMs). Traditional prefix-based reuse has low cache hit rates across inference requests because it requires exact token and position matches. To improve efficiency, recent system optimizations introduce position-independent KV reuse, allowing KV cache to be reused whenever identical text chunks appear, regardless of their position in the sequence. We show this design introduces a new threat, KV Cache Hijacking. Since KV caches are retrieved by token match but encode the context in which they were originally computed, the KV tied to a benign-looking token chunk may encode an attacker-controlled prefix. When later reused in a victim query, this contaminated KV silently hijacks the model's behavior, even if no attacker-controlled text appears in the input. We introduce HIJACKKV, the first attack framework that systematically exploits this vulnerability, demonstrating its severity and practicality. HIJACKKV optimizes an attacker-controlled prefix, so that the KV computed for a subsequent common benign text encodes the attacker's goal, while the text remains unchanged for future cache hits. HIJACKKV achieves an average 94% success rate in a single attempt, remains effective under realistic constraints including low hit rates (10%) and frequent recomputation (50%), persists over multi-turn interactions, and transfers across models in black-box settings. We further provide design insights for building secure KV reuse systems.

Yichi Zhang, Zhiqi Wang, Huan Zhang +1

The Pennsylvania State University · University of Illinois Urbana-Champaign

KV Caching LLM Security KV-Cache Reuse

Jul 21, 2026cs.CV

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning

Long-video question answering requires a model to preserve visual evidence over time without repeatedly reprocessing the same video. A practical approach is to store the vision-language model's internal key-value (KV) cache for each video chunk and retrieve that state at query time. However, independently cached video chunks do not compose correctly: every chunk is prefilled from local rotary position zero, so naive concatenation collides temporal phases and removes the global order required for questions about what happened first, how often events occurred, or what changed across the video. This paper presents ChronoStitch, a training-free method for composing independently stored visual KV memories. The method first re-bases stored post-rotary keys onto a global three-axis multimodal RoPE coordinate system that preserves time, height, and width structure. We show why a one-dimensional scalar re-indexing is geometrically inconsistent for visual tokens because it turns spatial order within a frame into false temporal displacement. We then address the residual content gap left by positional repair: later chunks were originally encoded without attending to earlier chunks. ChronoStitch therefore selectively recomputes a small fraction of high-deviation later-chunk visual tokens while allowing them to attend over the composed cache. On Qwen2.5-VL-3B and the temporal split of TempCompass, ChronoStitch outperforms naive composition and position-only variants, improving event-ordering accuracy while running 3.3x faster than full joint re-prefilling.

Santiram Tiwari, Nishant Sinha, Kunal Kislay

KGraph AI Solutions Pvt. Ltd., Bangalore, India – 560016

Memory-Augmented VLMs KV Caching Temporal Reasoning Long-Video QA Temporal QA Temporal Video Understanding

Jul 21, 2026cs.LG

MoA-Structured Decode Attention DNF Derivation, KV-Cache Accumulation, GQA/MQA, and OpenACC Kernel

We derive four memory-optimal inference artifacts for transformer attention using the Mathematics of Arrays (MoA), each following directly from the forward-pass Denotational Normal Form (DNF) of with the query-row index fixed to the current decode step. The artifacts are: (1)~a single-query decode DNF in which the

ψ

-reduction eliminates the

K^\top

buffer algebraically, achieving

(d_k + nd_k+ nd_v+ d_v)\times4\,{B}

Dynamic Random Access Memory (DRAM) traffic result numerically verified to

\|{err}\|_\leq2\times10^{-7}

; (2)~a C/OpenACC Graphics Processing Unit (GPU) kernel with Operational Normal Form (ONF) stride arithmetic and hardware-coalesced memory access, verified to

\|\mathrm{err}\|_\infty=0

(exact IEEE-754 floating-point arithmetic); (3)~a multi-step KV-cache with

O(d_k+d_v)

per-step append via MoA concatenation

\#

; and (4)~Grouped-Query Attention (GQA) and Multi-Query Attention (MQA) derived via

ψ

-selection, achieving a proven

\frac {h_q} { h_{kv} }

reduction in KV traffic. All programs are verified against PyTorch scaled_dot_product_attention.

Lenore Mulin, Gaetan Hains

University at Albany, SUNY · LACL, Universit´e Paris-Est Cr´eteil

Efficient Transformer Inference Grouped-Query Attention Transformer Inference GPU Kernel Optimization KV Caching Memory-Efficient Optimization+2

Jul 20, 2026cs.CL

C $^2$ KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference

Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation and multi-document reasoning. To mitigate the growing inference cost, recent work has explored 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 C

^2

KV, a unified framework for non-prefix KV reuse that jointly optimizes KV extraction and inference-time concatenation. C

^2

KV 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 C

^2

KV significantly reduces KV cache storage and transfer costs, achieving up to 17

\times

inference speedup under long contexts, while preserving generation quality.

Chuheng Du, Junyi Chen, Hanlin Tang +7

School of Computer Science Shanghai Jiao Tong University Shanghai, China · Alibaba Group Hangzhou, China

KV Caching LLM Inference Acceleration KV-Cache Reuse KV-Cache Compression Long-Context Inference

Jul 19, 2026cs.LG

Regularize or Localize: When Training-Time KV-Cache Geometry Pays Under Quantization

We study whether \sigreg -- LeJEPA's anti-collapse objective -- can reshape representations during standard autoregressive language-model pretraining, and when the resulting geometry helps \kv-cache quantization. We train 110M-parameter models on 10B FineWeb tokens and report three findings. \textbf{(1)} At

λ{=}0.01

, \sigreg reduces hidden-state pairwise-cosine anisotropy by

38\%

across three paired seeds. Perplexity increases by less than

0.35\%

in every pair, with no consistent zero-shot loss. \textbf{(2)} This change does not propagate from hidden states to the \kv cache. Applying \sigreg directly to K and V during continued training, however, reduces mean cache anisotropy by

94\%

across four checkpoints. A matched continuation without the \kv term leaves cache geometry nearly unchanged, and the frozen-trunk retrofits we tested do not reproduce the effect. \textbf{(3)} Under untransformed symmetric group-free quantization, direct \kv regularization is the only training condition that prefers per-channel scaling in all three seeds, and under that same 3-bit per-channel scheme the baseline incurs

4.3

--

7.9\times

the directly regularized model's \dnll. Under the full simulated KIVI-style configuration (mixed arrangement, zero-points, grouped scales), however, all models reach near-parity, including when storage overhead is approximately matched. In this 110M regime, the training intervention helps when quantizer scales are coarse; the advantage vanishes under the tested combination of token-local grouping, mixed \kv scaling, and zero-points. To our knowledge this is the first training-time \emph{distributional} regularization of standard \kv-cache geometry evaluated against post-hoc cache quantization.

Libo Sun, Po-Wei Harn, Zewei Zhang +2

Department of Computer Science and Software Engineering, Auburn University, Auburn, AL 36830, USA · Department of Information Management, National Central University, Taoyuan 320317, Taiwan

KV Caching Attention Quantization Representation Geometry in Language Models KV-Cache Quantization

Jul 16, 2026cs.RO

Reflex: Real-Time VLA Control through Streaming Inference

Flow matching Vision-Language-Action (VLA) models promise precise continuous control, but their iterative denoising nature introduces fundamental incompatibilities with real-time robotics: global timestep injection invalidates KV-caching, forcing a choice between slow

O(N^2)

re-computation or mathematically incorrect cache reuse. We present \textbf{Reflex}, a framework that enables \textit{real-time streaming inference} for flow matching policies by exploiting the \textit{Timestep-Invariance Property} -- that perception encoders are functionally independent of the denoising loop. Reflex partitions the attention context into static, sliding, and dynamic regions, enabling

O(1)

incremental cache updates while preserving full-batch-equivalent attention outputs for fixed inputs. To ensure stability under continuous high-frequency inference, we introduce \textit{AdaRMSNorm}, an adaptive normalization layer that prevents BFloat16 numerical collapse by gating on flow phase. We further maximize throughput through an \textit{async pipeline} that decouples visual encoding from action generation, combined with \textit{operator fusion} that reduces kernel overhead. On LIBERO and Kinetix benchmarks, Reflex achieves a 2.58

\times

inference speedup and 50Hz stable streaming, reducing reaction latency by up to 54% and enabling efficient deployment without performance degradation.

Yuanchun Guo, Bingyan Liu

School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China.

Flow Matching KV Caching Efficient VLA Model Inference Vision-Language-Action Models

Jul 15, 2026cs.CL

Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel

We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a byte-exact key-value (KV) state artifact and later restored, by graft, into a fresh inference context. The restore is bit-exact: under a pinned deterministic configuration, the grafted logits are byte-for-byte identical to a fresh computation (SHA-256 equality), with zero KL divergence and 100% argmax agreement over fifty samples. We show that own-position graft is the unique numerically exact operating point on a model with floating-point rotary encoding, and we verify byte-exactness on two model scales (12B, 31B) and two GPU targets, one through a pre-registered replay. On AIME 2025, a frozen Gemma-4-12B moves from 80.0% to 93.3% once a verified solution library is grafted, above its own 77.5% and its 31B sibling's 89.2% published anchors. On the recurring case, eight problems the base model never solves within a 401,026-token budget are answered from cached verified solutions in 61 total decode tokens, a factor of 6,574 fewer tokens and about 8,700x less energy; the capability claim proper rests on held-out transfer (7 of 7 at 31B). The same byte-exact store widens usable context from 32,768 to 2,854,766 tokens at zero extra accelerator memory, and moves byte-identical between machines of the same architecture. We describe the system at the behavior level; the engine is proprietary, and every reported number is backed by committed input and output hashes so the scoring can be re-checked without it.

Sietse Schelpe

Corbenic AI

Memory-Augmented Language Models Knowledge Augmentation for Language Models KV Caching Long-Context Language Model Inference LLM Inference Acceleration KV-Cache Reuse

Jul 14, 2026cs.CL

Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference

Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accumulated attention mass, treated here as signal energy, and keeping the heaviest. On schema-dense input streams such as nested JSON, this score acts as a non-stationary filter that disproportionately retains noise: a non-content sink role (delimiters or whitespace) carries an order of magnitude more energy than any content role, and structural KEY tokens are over-retained at roughly 1.8x the rate of the answer-carrying VALUE tokens, collapsing exact-match accuracy from 88% to 0% at a 5% budget as the signal-to-noise ratio of the retained state degrades. A counterfactual experiment establishes that suppressing KEY tokens is the best deployable filter. Our retraining-free, role-conditional allocation over SnapKV's windowed score, governed by a single tuned hyperparameter, closes 63-98% of the H2O gap at sub-20% budgets and, at higher budgets, modestly matches or exceeds full-cache accuracy -- a small, seed-sensitive denoising effect (borderline significant at B=0.50; not distinguishable from zero at B=0.30 over four seeds). A 15 MB linear role probe supplies these labels at negligible inference cost, though matching parser-level downstream accuracy remains open.

Soumil Mandal

ServiceNow

KV Caching Long-Context Language Model Inference Memory-Efficient Optimization KV-Cache Eviction KV-Cache Pruning

Jul 14, 2026cs.LG

A JoLT for the KV cache: Near-Lossless KV Cache Compression via Joint Rank-bit Allocation

The key-value (KV) cache is the dominant memory bottleneck in long-context language model inference. Existing compression methods apply low-rank factorization or quantization independently, without jointly allocating rank and precision under a shared storage budget. We introduce JoLT, a training-free compressor that treats grouped prefill caches as fourth-order tensors and applies partial Tucker decomposition along the token and feature modes, the two axes that carry low-rank structure, while leaving the head and layer modes intact. A rotated low-bit quantizer captures the truncation residual, and a single Lagrangian dual allocates per-group Tucker ranks and residual bit-widths under a global byte constraint. FlashJoLT replaces the exact token-mode SVD with a randomized approximation that matches JoLT within the free zone at a fraction of the compression cost, and a fused Triton decode kernel evaluates attention directly over the stored factors without materializing dense KV tensors. Across five models from four architecture families, covering multi-head attention, grouped-query attention, and mixture-of-experts architecture, JoLT achieves 2 - 3x compression with less than 0.2% perplexity degradation, without retraining. On RULER at 64K context with LLaMA-3.1-8B, retrieval accuracy remains near-lossless through 3x and declines by only 0.90 and 2.40pp at 4x and 5x, respectively. JoLT demonstrates that tensor-aware low-rank decomposition and quantized residuals, unified under a single storage budget, achieve near-lossless KV-cache compression across diverse model architectures without retraining.

Rahul Krishnan, Volker Schulz

Universität Trier · Fachbereich IV, Mathematik, Universität Trier

KV Caching Low-Rank Matrix Decomposition Tensor Decomposition Low-Rank Compression Low-Rank Approximation KV-Cache Compression+1

Jul 14, 2026cs.AR

Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit

We present a full-pipeline inference optimization for the MiMo-V2.5 model family, which combines Hybrid Sliding Window Attention (Hybrid SWA), sparse Mixture-of-Experts (MoE), and multimodal encoders. While Hybrid SWA can ideally reduce both attention compute and KVCache storage significantly compared to Full Attention, realizing these gains in production requires substantial engineering effort. We systematically optimize the KVCache system with layerwise prefetch, SWA-aware prefix cache trees, and specialized placement strategies, achieving strict

O(W)

SWA storage and high cache hit rates. We further build GCache, a high-performance distributed cache infrastructure with RDMA-optimized networking, and develop a KVCache-affinity router to reduce computation while preserving load balancing. We also optimize for multimodal inputs, including GPU image preprocessing, parallel video decoding, and multimodal cache sharing. Together, these optimizations constitute the first large-scale LLM serving system in production that efficiently covers the Hybrid SWA + MoE + multimodal composite architecture.

Xiaomi MiMo Team, Anqi Liu, Aoxin Ma +28

MiMo Team, Xiaomi

Efficient Multimodal Inference KV Caching Memory-Efficient Optimization KV-Cache Management LLM Inference Serving LLM Inference Acceleration

Jul 12, 2026cs.LG

MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference

Large language model (LLM) agents accumulate heterogeneous context, including system instructions, plans, user turns, retrieved documents, tool outputs, and intermediate reasoning, whose key-value (KV) cache can become a major memory bottleneck. Existing eviction policies generally apply the same attention- or recency-based rule to every token, ignoring semantic structure already available to the agent orchestrator. We introduce MemDecay, a training-free, region-aware KV-cache eviction policy. MemDecay assigns tokens region-specific base priorities and decay rates, refreshes retention scores when tokens receive attention, and evicts the lowest-scoring pages under a fixed cache budget while allowing critical regions to be pinned. We also provide a procedure for calibrating decay rates from measured attention lifetimes. We evaluate MemDecay at approximately 450 and 1,700 token contexts using Qwen2.5-1.5B and 3B. Across all settings, attention lifetimes differ by an order of magnitude across regions: system-token half-lives range from 148 to 189 decoding steps, compared with 14 to 16 for scratchpad tokens. Pinning preserves system-region facts at full-cache accuracy in every setting, while no baseline preserves more than 13 of 24. Region-aware retention remains effective as context grows, whereas recency-based retention collapses. Accumulated-attention retention performs better on unpinned content, however, and ablations identify attention-score normalization as the main limitation of the current formulation. These results establish semantic prompt structure as a robust signal for KV-cache management while clarifying how it should be combined with attention-based importance.

Venkatesha Matam, Keon Kim

Independent Researcher New York City, USA

KV Caching KV-Cache Eviction KV-Cache Management LLM Inference Acceleration

Jul 11, 2026cs.LG

How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit

KV-cache compression methods are predominantly evaluated with the query appended to the context before compression -- a query-aware protocol. Yet the economic case for a compressed KV cache is reuse: compress a document once, answer many future questions against it. In that deployment, compression must happen query-agnostic -- before any question is seen. We present a matched-budget audit of six published compression methods against three trivial baselines on three open 7-9B models (144,300 paired evaluations on RULER-8192; 40,800 on LongBench; 50,000-resample paired bootstrap throughout). Everything is held fixed -- model, compression ratio, instances, decoding -- except the scoring rule. Three findings. (1) Query visibility changes the rankings: under the agnostic protocol, of the five audited methods that share a common attention backend, only KeyDiff beats a best-of-3 trivial baseline consistently (31 of 36 cells), and the most widely deployed method, SnapKV, loses to "keep the start and the recent window" on average (-0.066). (2) The per-method drop between the two protocols is ordered consistently with how visible the question is to each method's scoring signal, legible in its source code: from Delta=+0.198 for SnapKV (the question sits inside its 64-token observation window) down to Delta=+0.011 for KeyDiff (its score contains no query term at all).

Daming Luo, Christy Liang, Junyu Xuan

University of Technology Sydney

KV Caching KV-Cache Reuse KV-Cache Compression

Jul 10, 2026cs.LG

Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention

Fixed-state sequence models compress an unbounded past into a bounded state, which caps their associative recall at roughly the state dimension; attention escapes the cap by keeping a key-value entry for every token, at quadratic compute and a cache that grows with the sequence. We study the middle ground: a sparse cache that allocates a slot only when an input is novel, so its size tracks the number of distinct items rather than the number of tokens. The allocation rule is the DP-means clustering rule, the small-variance limit of a Dirichlet-process mixture, used not as latent-variable inference but as the key-value memory operator for a deep recurrent backbone. We develop it in two forms, a static cache with a fixed concentration and a surprise-adaptive variant whose concentration follows the recent novelty rate. On a controlled associative-recall benchmark with redundancy we show that the cache matches full-attention recall while storing only the distinct items, that it dominates a fixed-budget eviction cache on the recall-versus-size frontier, and that on a state-space backbone it answers both a recall query and a long-range aggregate at the lowest memory of any model tested. The allocation is learnable end to end: a two-parameter novelty-threshold gate trained on the task loss alone recovers the rule exactly, whereas an over-parameterized gate fails, so the operative ingredient is the inductive bias rather than capacity. The evidence is a family of controlled mechanism studies at modest scale, with the distinct-items property confirmed on four real streams (recommendation, systems logs, clinical events, and insurance claims); a real-backbone, real-corpus language validation is pursued in a companion study.

Siddharth Pal, Viktoria Rojkova

Memory-Augmented Neural Networks KV Caching Associative Memory

Jul 10, 2026cs.AI

KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling

Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: they re-encode the entire trajectory text from scratch. In long multi-agent rollouts, the scoring cost, growing quadratically with respect to sequence length L, creates a severe computational bottleneck, severely limiting PRMs' application in long-context scenarios. To resolve this, we introduce KV-PRM, a highly efficient process reward model that eliminates the heavy text re-encoding by directly reading the KV cache produced naturally during the LLM's generation phase. By processing a single "verify token" against the pre-existing KV cache, KV-PRM reduces the scoring cost from O(L^2) to O(L). We formally prove that the KV cache contains strictly greater information capacity than text, and is more efficient for downstream reward modeling. Empirically, across the MATH, GSM8K, and AIME benchmarks, KV-PRM matches or strictly outperforms text-PRMs under various TTS methods such as Beam Search, MCTS, and Weighted Voting, with up to a 5,000x reduction in scoring FLOPs, a 37x reduction in latency, and a 34x reduction in per-sequence memory footprint compared to text-based PRMs.

Peng Kuang, Haibo Jin, Xiaoyu Han +5

University of Illinois Urbana-Champaign · Imperial College London · City University of Hong Kong

Process Reward Models KV Caching Test-Time Scaling KV-Cache Reuse Multi-Agent LLMs

Jul 10, 2026cs.LG

COBS: Cumulant Order Block Sparse Attention

Block sparse attention is a hardware friendly way to alleviate the key-value (KV) cache read bottleneck in large language models (LLMs). However, it is not prevalent among leading open-weight LLMs, which rely instead on dense attention or fine-grained selection, thereby motivating our analysis. We study DeepSeek's Native Sparse Attention (NSA) as a representative method, whose three-branch design lets us isolate block selection, the most challenging and consequential stage. We formalize selection and reduce it to ranking blocks by a single quantity, the attention mass: the sum of a block's attention scores. We show that if selection retrieves the blocks with the largest attention mass, block sparse attention can match the quality of dense attention. However, computing the exact attention mass requires reading every key, so the problem of block selection ultimately reduces to approximating this mass from a compact summary instead of the full keys. Via a cumulant expansion, we show why existing methods falter: their selection strategies attempt to estimate the attention mass, but are confined to a first-order approximation. Therefore, we propose COBS (Cumulant Order Block Sparse Attention), an attention method that builds on NSA, incorporating a novel selector that stores a compressed second-order statistic per block. On the 32k RULER long-context retrieval benchmark, COBS raises the NSA baseline's mean score from 0.2999 to 0.8195, approaching dense attention at 0.9040 and closing about 86% of the gap, while using only 1.21x the KV cache read traffic of the NSA baseline and 15.15x less read traffic than dense. The same model preserves short-context behavior and attains lower position-wise negative log-likelihood (NLL) than dense attention in our comparison.

Alexander Tian, Aditya Ghai, Sanjit Neelam +2

MatX

KV Caching LLM Inference Acceleration Block-Sparse Attention

Jul 9, 2026cs.LG

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In this survey, we focus on system-aware KV infrastructure for serving LLMs (abbreviated as sKis). We revisit recent work from a system behavior perspective, organizing existing efforts into three dimensions: execution and scheduling (temporal), placement and migration (spatial), and representation and retention (structural). Furthermore, we analyze cross-behavior co-design affinity and behavior-objective links, highlighting future opportunities. Our work systematizes a rapidly evolving area, providing a foundation for understanding and innovating KV cache designs in modern LLM serving infrastructure.

Jiantong Jiang, Peiyu Yang, Rui Zhang +1

School of Computing and Information Systems, The University of Melbourne · School of Computer Science and Technology, Huazhong University of Science and Technology (www.ruizhang.info)

LLM Inference Efficiency LLM Serving KV Caching KV-Cache Management

Jul 8, 2026cs.LG

Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference

The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantization, eviction, or offloading. We study a complementary question: once a position's KV state has been quantized to codebook indices, how should the resulting symbol stream be stored, and can the storage layer do more than store? A family of contractive iterated-map codes that serialize a symbol sequence into a sequence of low-dimensional real vectors is revisited, and it is shown that they form a natural archive format for a quantized KV cache with the following features. The method provides exactly the access pattern a growing cache requires. It is lossless, it runs in linear time, and supports O(1) random access and O(1) amortized append. A controlled study of the quantizer feeding this archive is conducted on GPT-2 with 1024-token contexts. Keeping a small exact window (4 attention sinks + 32 recent tokens) and archiving the rest, per-head residual vector quantization reduces the archived cache by 36-54x relative to an fp16 cache at a perplexity cost of 11-15%, and we quantify a sharp key/value asymmetry -- quantizing keys is roughly 4x more damaging than quantizing values, consistent with prior low-bit KV work -- and use it to allocate bits in a hybrid scheme. Finally, we show the archive is simultaneously a search index: approximate substring queries execute directly on the stored vectors, and matched context is decoded from the matched vector without ever materializing the surrounding text. We release all code; every number reproduces from a single command on a laptop CPU.

Vladimir Gusev

Independent Researcher

Residual VQ KV Caching Long-Context Language Model Inference KV-Cache Compression KV-Cache Quantization

Jul 7, 2026eess.AS

Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs

Speech large language models (Speech LLMs) typically encode speech into sequences far longer than text, creating a major efficiency bottleneck during autoregressive decoding. A common remedy is to compress the speech sequence at the adapter level to remove temporal redundancy before it enters the LLM; however, such early downsampling risks discarding fine-grained information that cannot be recovered. We propose SpeechKV, which applies a learned pooling to the KV cache of speech tokens inside the LLM. This design allows the LLM to fuse speech and text internally while directly accelerating decoding. Trained on 71K hours of speech data, SpeechKV compresses the speech to approximately text-level granularity yet maintains performance on par with or even slightly better than the uncompressed baseline, with relative gains of 6.6% on out-of-domain entity recognition and 2.3% on OpenASR, while delivering at least 1.49 times decoding speedup that scales with audio length.

Ke-Han Lu, Keqi Deng, Ruchao Fan +2

Microsoft, USA · National Taiwan University, Taiwan

KV Caching Automatic Speech Recognition LLM Inference Acceleration KV-Cache Compression Speech Language Models

Jul 7, 2026cs.AI

DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression

Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing compression methods often apply uniform budgets across layers or tokens and degrade retrieval when lexical cues and semantic states require different preservation. We introduce DepthWeave-KV, a token-adaptive cache compression method that factorizes key and value states across neighboring transformer layers using shared low-rank channel bases while retaining lightweight token-specific residuals where attention behavior is sensitive. DepthWeave-KV combines cross-depth residual factorization with a token-conditional depth router that allocates higher reconstruction rank to instruction-bearing and retrieval-critical tokens, and uses calibration-free online error tracking from attention-output probes to adapt compression during generation without retraining the base model. A fused CUDA implementation jointly performs basis lookup, residual dequantization, and attention projection to reduce decode-time memory traffic. Across LongBench, Needle-in-a-Haystack, L-Eval, and long-form QA and summarization benchmarks, DepthWeave-KV achieves near-full-cache task quality with substantially lower memory use, improving average score and retrieval accuracy over prior compressed caches while reaching 8.3x KV memory reduction and 72.8 tokens per second at 64K context.

Anna Cordoba, Adam Puente Tercero, Nerea Angulo Hijo +4

Instituto de Investigación en Visión Artificial

KV Caching Long-Context Language Model Inference Memory-Efficient Optimization LLM Inference Acceleration Low-Rank Compression KV-Cache Compression

Jul 7, 2026cs.AI

FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference

Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning. We introduce FreqDepthKV, an inference-time cache compression method that factorizes adjacent-layer KV states into shared low-frequency depth components and sparse high-frequency residuals. A lightweight online probe assigns attention heads to shared-depth, residual-depth, or exact cache modes according to their contribution to reconstruction-sensitive attention logits, allowing the compression policy to adapt to prompt structure without retraining. Across long-context question answering, needle retrieval, summarization, and code generation benchmarks, FreqDepthKV preserves task accuracy under substantially smaller cache budgets. With a 32k-token prefill window, FreqDepthKV reaches 58.3 Exact Match, 63.0 F1, 32.5 ROUGE-L, and 48.1 pass@1, closely matching full KV while outperforming prior compressed-cache methods. It also improves decoding throughput to 70.4 tokens/s, reduces TTFT to 2.06 seconds, and lowers peak KV memory to 6.2 GB, achieving a 3.9x effective compression ratio.

Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo +4

Instituto de Investigación en Visión Artificial

KV Caching Long-Context Language Model Inference Memory-Efficient Optimization LLM Inference Acceleration KV-Cache Compression

Jul 6, 2026cs.LG

KVpop -- Key-Value Cache Compression with Predictive Online Pruning

Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length. Existing KV eviction methods often rely on static heuristics or proxy scores, which poorly track future token utility and cause brittle eviction as relevance shifts. To address this, we introduce KVpop, which learns a fixed-budget KV eviction policy by directly supervising the keep-or-drop decision. The scorer is trained against a novel future-attention target, computed efficiently without materializing dense attention maps. We further introduce a delayed memory-based scorer that, uniquely among learned eviction methods, defers scoring for a fixed number of steps to exploit near-future context. On AIME and HMMT mathematical reasoning, KVpop retains 98% of full-attention performance on Qwen3-4B at 75% KV cache compression and 97% at 88% compression, consistently outperforming established eviction baselines. Qwen3-8B shows even stronger results, reaching near-full teacher performance. These results show that supervising eviction with future-attention signals cuts memory costs while maintaining quality.

Lukas Hauzenberger, Niklas Schmidinger, Anamaria-Roberta Hartl +5

1NXAI · 2Johannes Kepler University Linz, Austria

KV Caching KV-Cache Eviction LLM Inference Acceleration KV-Cache Compression Autoregressive Decoding KV-Cache Pruning

Jul 2, 2026cs.SD

Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving

Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for the whole conversation. This regime hides a dangerous failure mode. On a real full-duplex stack, sustained load does not degrade serving gracefully: it falls off a cliff, jumping in one step from milliseconds per frame to a stalled engine when accumulated session state exhausts the KV pool. The collapse is metastable -- identical five-minute runs collapse or survive on run-to-run variance -- and silent: latency and deadline-miss metrics read healthy throughout. We show one move restores both stability and observability: bound each session's resident state, and latency starts telling the truth. Metronome's in-engine KV window eliminates the collapse (0/20 vs. 14/20 runs across two batches) and turns per-frame latency into a monotone load signal, on which an online admission controller discovers the schedulable concurrency; without the window, the identical controller over-admits into the wall. A first-order model predicts the collapse time within a few percent on the headline model, and a quality probe validates the bound's design by ablation: the window alone is quality-free in turn-based decoding, and its few pinned attention-sink tokens are what keep free-running generation healthy. Everything is measured end-to-end on real audio, across four interaction models on one GPU.

Jiaying Meng, Bojie Li

Independent Researcher · Pine AI

LLM Serving KV Caching KV-Cache Management Online Resource Allocation

Jul 2, 2026cs.AI

A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets

Linear-attention and state-space language models compress the prefix into a fixed-size recurrent state, yielding O(1) memory at the cost of a lossy exact memory: when many key--value associations compete, earlier facts are overwritten and needle recall degrades. Inspired by Complementary Learning Systems, we give linear attention a hippocampal complement. HOLA (Hippocampal Linear Attention) keeps the usual delta-rule state as a compressive memory and adds a bounded exact KV cache, forming a semiparametric test-time memory: the state models linearly compressible structure, while the cache stores associations that should not be forced through that state. The cache writes without a learned eviction module, keeping tokens with large beta * ||e||, the prediction residual actually committed to the state; a decoupled RMSNorm-gamma cache read then turns these exact KV pairs into sharp retrieval rather than soft averaging. At 340M parameters trained on 15B SlimPajama tokens, HOLA lowers Wikitext perplexity from 27.32 to 22.92 (-16.1%), below a full-attention Transformer++ (26.88), and improves LAMBADA perplexity from 30.95 to 30.26. It also achieves the best linear in-context retrieval and remains much more robust than GDN or a matched HOLA+recency cache on RULER needle-in-a-haystack recall out to 32k tokens (16x its training length).

Wanyun Cui

Shanghai University of Finance and Economics

Long-Context Retrieval Memory-Augmented Language Models KV Caching Long-Context Language Modeling Persistent Memory for Language Models Delta-Rule Linear Attention+1

Jul 2, 2026cs.AI

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time. We study fixed-footprint continual adaptation: the deployed adaptation state is kept under a fixed memory budget, while the backbone model is left unchanged and task-specific updates are externalized. We propose InduceKV, a retrieval-based method that stores each selected training prefix as an attention-ready memory entry, consisting of a frozen retrieval key and compact layerwise key--value (KV) payloads that can be appended to the model's self-attention cache. Under a strict memory budget, InduceKV constructs a compact inducing set through bilevel selection: a lightweight calibration is fit for retrieval, while the selected memory balances current-task likelihood, anchor-based retention, and coverage in the frozen retrieval space. Across task-incremental instruction tuning, continual VQA, domain-incremental adaptation, and lifelong multimodal instruction tuning, InduceKV consistently improves over PEFT, MoE, replay, and prompt-retrieval baselines under matched memory budgets. We further report backbone-matched, stage-1 CoIN, compute-matched, and scalability diagnostics, showing that the gains are not due to a stronger backbone, replay alone, or an unbounded candidate pool.

Qianyu Chen, Ziteng Feng, Canran Xiao +1

1Nanyang Technological University · University of Science and Technology of China · 3Shenzhen Campus of Sun Yat-sen University

Continual Learning for LLMs Memory-Efficient Fine-Tuning Memory-Augmented Language Models VLM Adaptation KV Caching Multimodal Large Language Models+2

Jul 2, 2026cs.DC

Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference

Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems. In disaggregated inference, these workloads require transferring large Key-Value (KV) caches across the network, where decoding cannot begin until the transfer completes. Recent KV quantization techniques reduce data volume and alleviate this bottleneck, but existing schemes fail to achieve both low network-exposed latency and high inference accuracy. We challenge the assumption that the KV cache is an indivisible unit that must be fully received before use. We leverage the observation that different bits in the KV cache contribute unequally to attention computation and inference precision: the most significant bits capture the coarse structure of attention and the least significant bits refine precision. This property enables partial use of the KV cache during decoding. We present Lynx, a system that enables progressive, split-stream KV transfer by partitioning the KV cache into a high-priority Anchor stream carrying the most significant bits and a low-priority Residual stream carrying remaining precision. Decoding begins upon receipt of the Anchor stream and proceeds speculatively while the Residual stream is transferred concurrently, followed by verification that ensures equivalence to higher-precision decoding. Across multiple models and serving workloads, Lynx achieves Time-to-First-Token (TTFT) comparable to aggressive 4-bit KV quantization, while matching the accuracy of high-precision (BF16) inference, improving TTFT over standard 8-bit KV quantization by up to

1.43\times

and improving accuracy over state-of-the-art by up to

5.1\%

.

Wenchen Han, Gingfung Matthew Yeung, Marco Barletta +3

University College London · Huawei

LLM Inference KV Caching Long-Context Language Model Inference KV-Cache Management LLM Inference Acceleration KV-Cache Quantization

Jul 1, 2026cs.LG

The risk of KV cache compression

Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache. The prevalent approach to this bottleneck is KV cache compression, which replaces the full cache with a compact summary. Despite its practical importance, the design of such summaries is largely driven by empirical experimentation. On the theoretical side, existing results show that KV cache compression can be impossible in the worst case, but offer little systematic guidance for designing algorithms in regimes where accurate compression is possible. We bridge this gap by characterizing the minimax risk of KV cache compression in terms of the intrinsic compressibility of a cache, revealing when and how accurate compression is possible. These results yield novel design principles for KV cache compression under causal masking that map efficiently to prefill and autoregressive decoding while achieving minimax-optimal risk. We instantiate these principles in a practical algorithm and report promising performance on LongBench in targeted experiments. Overall, our results provide a principled avenue for practical KV cache compression with theoretical guarantees.

Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno +2

RWTH Aachen University · Stanford University

Transformer Inference KV Caching Memory-Efficient Inference KV-Cache Compression

Jul 1, 2026cs.DS

Precomputing the Future-Offset Average in TriAttention

TriAttention is a recent method for shrinking the KV cache of long-reasoning LLMs: it scores each cached key by how much attention it is likely to receive and evicts the lowest-scoring ones. Because a key does not know how far away its future queries will sit, the score is averaged over a ladder of 17 possible future distances. We point out that this average is free: the future distance enters the score only through the position-dependent rotation, so the whole 17-fold average collapses--exactly, by a one-line algebraic identity--into a single per-band weight that is computed once, offline. Scoring a key then costs one evaluation instead of seventeen, with no change to which keys get pruned. The saving is modest and lives entirely in TriAttention's pruning-score computation, not in the attention kernel; we present it as a small, exact complement to their method, and we confirm the identity numerically.

Amarnath Mukherjee

Hozhoke, Inc.

LLM Inference Efficiency KV Caching KV-Cache Management KV-Cache Compression KV-Cache Pruning

Jul 1, 2026cs.MA

Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning

Multi-agent latent reasoning composes agents' KV-caches into one context for a final agent. Prior work (Agent Primitives) does this by concatenating caches along the sequence axis with RoPE re-encoding, which we call BagMerge. BagMerge is non-commutative, and the best input ordering is unpredictable, shifting with the regime, the latent-step budget, and the model scale. We make this exchange a convergent replicated state. First, CanonicalMerge fixes the layout by content: ordering caches by mean K-norm at a middle layer renders the merged cache byte-identical under any input permutation, verified algorithmically (arity N<=5) and bit-for-bit on real Qwen3-1.7B and 4B state. Second, we separate the replicated state from decode-time layout: the state is a set of content-addressed latent fragments whose merge is set union, a state-based CvRDT (commutative, associative, idempotent, absorbing), and CanonicalMerge is its deterministic render. Because the render is byte-equivalent, every N=2 accuracy number carries over unchanged and re-delivered duplicates are absorbed rather than re-concatenated. On a partitioned-reasoning benchmark, CanonicalMerge matches the best BagMerge ordering in every regime-by-budget-by-ordering cell without knowing which order is best, trading a small, statistically insignificant accuracy margin for an unconditional structural guarantee. The behaviour transfers to real multi-document QA (HotpotQA), while the closest training-free output-fusion baseline (PackLLM) loses by 45 points at matched budget, placing cache-level merging in a regime distinct from output-level fusion. Finally, at k>2 the approach transports and colocates latent traces but does not by itself compose them, which we characterize to motivate future work.

Carlos Baquero, Luís Brito

Faculdade de Engenharia (FEUP), Universidade do Porto (UP), Portugal · Escola Superior de Tecnologia e Gestão (ESTG), Politécnico de Viana do Castelo (IPVC), Portugal

KV Caching Language Model Merging Multi-Agent Reasoning