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

Sep 24, 2026cs.DC

When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse

Long-running LLM applications repeatedly send growing context, making prefix caching critical for reducing prefill cost. Yet prefix-cache behavior under agentic workloads remains poorly understood. We study production traces from two companies and evaluate 14 eviction algorithms across HBM-constrained and large memory-pool settings. Despite a large gap to Belady, sophisticated policies designed for traditional caches provide little benefit over LRU. The reason is structural: prefix reuse is dominated by the regular pacing of active sessions, making recency unusually predictive. Prefix caching nevertheless introduces new challenges, including heavy-tailed session footprints and highly variable miss costs as attention computation grows with sequence length. We introduce the compute-savings ratio and two offline oracles to quantify these effects. Our results show that effective prefix-cache management should retain recency as its foundation while selectively adding quick demotion for one-hit prefixes, compute-aware partial eviction for expensive misses, and capacity-dependent eviction granularity. We will release the traces and simulator to support future research.

Yiyu Liu, Minlan Yu, Juncheng Yang

Harvard University

LLM Inference Efficiency KV Caching KV-Cache Eviction Prefix Caching Agent Memory Management

Sep 23, 2026cs.LG

Shared Global KV with Layer-Specific Local History

Decoder-only Transformer language models cache keys and values (KV) to reuse past computation during generation. Sharing KV across layers saves storage but reduces the diversity of representations available across depth. We study what local memory should retain alongside shared global KV, separating historical content from the input source used to form it. At 126M parameters and 2K context, an eight-seed study finds about 1.4% lower held-out test perplexity with local history than with a current-token local branch. Capacity, entry-count and training-compute controls support the value of historical content. In a two-seed comparison, this value persists when adjacent layers share local inputs while retaining independent projections; source sharing also shortens exact cache-construction dependencies. Against GQA and adjacent-layer KV sharing, equal bounded learning-rate searches and new-seed confirmation yield better same-source likelihood with larger caches and higher long-request latency. The ordering against adjacent-layer sharing persists after equal-token adaptation to 8K, with a short-context cost. The eight-seed external-book history effect remains uncertain, and downstream outcomes vary by task. We derive a sufficient suffix schedule that reduces upper-layer construction work while preserving the complete cache in exact arithmetic.

Xinglang Xian

KV Caching Long-Context Language Model Inference KV-Cache Management Transformer Attention

Sep 21, 2026cs.CL

Written as a Record, Read as an Address: What a Forward Pass Leaves in an Operation's KV Cache

When a language model reads an operation such as "Swap the contents of Box F and Box B", its forward pass writes keys and values for those tokens into the KV cache. Prior work on entity tracking establishes what models use: bindings are resolved at query time rather than stored as explicit latent state. We ask what they write at the operation span and how it is accessed. We split a forward pass into a frozen writer and a reader: the writer's cache is recomputed without gradients, while the reader sees only the instruction and operation tokens, with all state descriptions hidden, and is trained in isolation. Anything the reader recovers was therefore already present in the unmodified cache. On a synthetic boxes task, a base reader recovers

\leq 0.06

of queried bindings against

0.75

--

1.00

after training, and recoverability tracks the operation's read/write footprint. We find two modes of access. Across Llama-3.1-8B and Mistral-7B, operation-span transplants causally redirect which visible state is read even when the two worlds hold identical values, revealing a routing record. Isolation training preserves routing and adds direct access to the payload, the value the operation read, from the single operand-name token in a narrow mid-depth band (layers 12--15 of 32 in Llama-3.1-8B, 14--17 in Mistral-7B) --- the same site that holds the routing record. The same recipe extends to further operations, ToMi and GSM8K, but is bounded by training coverage and costs open-book accuracy. Operation tokens thus leave localized, causally recoverable records that support both routing and direct payload access, though the model that writes them reads mainly the address they carry and not the value.

Lingfeng Wu, Behzad Shomali

University of Bonn · Lamarr Institute

KV Caching LLM Interpretability

Sep 17, 2026cs.CL

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transfer bandwidth. Together, these compute, storage, and bandwidth demands constitute the primary bottleneck to further lowering deployment costs. To address this challenge, we introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. With its Causal Encoder-Decoder (CED) architecture, the model activates 16B parameters per token during decode but only 8B parameters during prefill, substantially improving cost efficiency for agentic workloads. To push the limits of KV cache compression, DeepSeek-V4.1-Flash combines cross-layer KV cache reuse in Compressed Sparse Attention 2 (CSA2) with FP4 KV caching. These designs reduce its global KV cache footprint (always in HBM) to 890 bytes per token, roughly 1/4 of the corresponding footprint of DeepSeek-V4-Flash. Further, through a dedicated deployment optimization known as SWA Bounded Replay, DeepSeek-V4.1-Flash reduces its persistent KV cache footprint (always on SSD or in host memory) to roughly 1/8 of that of DeepSeek-V4-Flash. Despite its much smaller KV cache footprint, the model delivers substantially better performance than the baseline. In addition, we streamline the DeepSeek-V4 architecture and introduce several efficient architectural extensions. We pretrain DeepSeek-V4.1-Flash on a multimodal corpus comprising 45T tokens and conduct comprehensive post-training, yielding strong performance across diverse text-based and multimodal agentic scenarios. Model checkpoints are available at https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash.

DeepSeek-AI, :, Anyi Xu +590

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

Sep 17, 2026cs.CL

D-Quant: Driftable Entropy Coding for KV Cache Quantization

The KV cache has become a major bottleneck in deploying LLMs, as its memory footprint grows linearly with sequence length and batch size, imposing substantial pressure on both memory capacity and bandwidth. Among various KV cache compression techniques, quantization is particularly attractive due to its effectiveness and ease of deployment. However, most existing methods rely on fixed-width quantization, where a

b

bit representation is inherently limited to

2^b

quantization levels. As the bit width decreases, the number of available levels shrinks exponentially, leading to severe information loss and rapid performance degradation. We further observe that fixed-width quantization fails to exploit the highly non-uniform distribution of KV cache. After rotation and normalization, KV values approximately follow a normal distribution, with most values concentrated near the center and only a small fraction appearing in the tails. Nevertheless, fixed-width coding allocates the same number of bits to frequent and rare symbols. Entropy coding naturally exploits such non-uniformity by assigning shorter codewords to frequent symbols and longer ones to rare symbols, substantially reducing the average number of bits required for representation. However, its variable-length output is not suited to highly parallel attention kernels, where efficient dequantization and computation rely on regular memory layouts and fixed-stride accesses. To bridge this gap, we propose \textbf{D-Quant}, a flexible KV cache quantization framework that introduces a \textbf{drift} mechanism to convert entropy-coded representations of each token into fixed-size bitstreams, enabling regular memory access and parallel dequantization within attention kernels.

Yi Su, Hong Liu, Guanghua Yu +1

Tencent

KV Caching KV-Cache Compression KV-Cache Quantization Entropy Coding

Sep 17, 2026cs.PF

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving

Repeated prompt prefixes are increasingly common in LLM serving workloads, appearing in system prompts, templated retrieval-augmented generation pipelines, agent frameworks, and multi-turn conversations. Modern inference runtimes such as vLLM and TensorRT-LLM provide mechanisms for reusing previously computed KV-cache state across requests, yet it remains unclear when prefix reuse materially improves serving performance on contemporary accelerators and when its benefits are limited by scheduling, cache granularity, concurrency, or memory pressure. This paper presents PrefixBench-H100, a reproducible benchmark and measurement framework for characterizing prefix reuse on a single NVIDIA H100. PrefixBench-H100 combines controlled synthetic traces with chat-style and retrieval-style workloads, and evaluates two widely used LLM serving runtimes under matched workload conditions. The benchmark varies shared-prefix length, suffix diversity, request arrival pattern, concurrency, output length, and cache configuration, while collecting time-to-first-token, inter-token latency, end-to-end latency, throughput, cache-hit statistics, GPU memory usage, and selected profiling traces. The goal of PrefixBench-H100 is not to introduce a new caching algorithm, but to expose the practical operating envelope of prefix reuse for H100-class LLM serving. The study identifies the regime where prefix reuse provides substantial first-token latency reductions and the regime where cache pressure erodes them, while showing that cache effectiveness itself is largely insensitive to concurrency and output length; the cross-runtime differences that remain arise above the cache, in the scheduling layer.

Omkar Shewale, Deepak Kumar, Divakar Kumar Yadav

Illinois Institute of Technology · University of Wisconsin–Milwaukee

LLM Inference Efficiency LLM Inference KV Caching LLM Inference Scheduling Prefix Caching

Sep 16, 2026cs.DC

Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It

An agentic request spends substantial wall-clock time waiting for tools, and its KV cache holds GPU memory the whole time. Serving systems decide whether that cache stays, leaves, or comes back by guessing how long the tool will run, from the tool's name, its history, a duration declared before the call, or the engine's own occupancy. We show that no estimate fixed before a call starts can know its duration, and such estimates may not even rank the calls. Meanwhile, the running tool already holds the answer, but the agent stack together with the tool silences it. We propose that tool calls report their progress explicitly while they run, and we measure what that takes. A census of four public agent corpora finds a readable signal in most tool time once it is revealed, in two strengths: a fraction of the work remaining, or an accurate signal that the end is near. A harness recovers it without changing what the agent sees, at no measurable cost to the agent's benchmark score. At the points where a KV cache decision is made, the reported progress is between several times and an order of magnitude more accurate than the best published predictors, and it stays accurate when the environment changes. Plugged into a production engine through a few small hints, it cuts the p90 time to first token (TTFT) after a tool call by 20.7% (HBM only) and 20.8% (HBM + DRAM) against LRU, close to an oracle. A serving system should not guess what its tools can tell it.

Yipeng Liu, Yingqiang Zhang, Feifei Li +1

Tsinghua University, China · Alibaba Cloud Computing, China · Zhejiang University, China

LLM Inference Efficiency KV Caching KV-Cache Management LLM Agent Workflow Optimization LLM Inference Serving LLM Agent Serving+2

Sep 16, 2026cs.AR

MeshKV: A Network-on-Chip KV Cache Fabric for Scalable Transformer Decoding Accelerators

Autoregressive transformer decoding is constrained by irregular key-value (KV) cache movement on tiled accelerators. Prior compression and DRAM-placement systems still concentrate traffic on centralized memory paths that bottleneck long-context serving. We present MeshKV, a KV cache fabric that moves blocks as packetized flows over a lightweight NoC. It co-designs (i) TaKV affine striping to spread homes and cut hotspot load, (ii) Mare multicast with verified duplicate suppression, and (iii) Pad, which overlaps prefetch, tile multiply, and streaming softmax behind credit-aligned FIFOs. Together they convert bisection back-pressure into useful KV transfer. On our 8x8 FPGA implementation with LLaMA-2-7B and Mistral-7B at 8K-32K, MeshKV reduces interconnect traffic by up to 58%, improves KV bandwidth utilization by 2.1x, and delivers up to 1.9x multi-stream throughput.

Dong Liu, Yanxuan Yu

Columbia University New York, NY, USA

Transformer Inference KV Caching KV-Cache Management FPGA-Based Neural Network Acceleration

Sep 16, 2026cs.AI

Contiguity, Not Importance: Budgeted Repair of Stale KV Caches After Document Edits

KV-cache reuse can reduce inference cost in retrieval-augmented generation and agentic systems, but cached contexts may become stale when retrieved knowledge, working memory, or user state is edited. Under causal self-attention, even a local edit can affect downstream KV states. A full re-prefill reliably restores consistency but is costly, whereas refreshing only the edited span can leave downstream dependencies stale. We formulate in-place repair as budgeted recomputation and compare training-free position-selection policies on a factual RAG benchmark with matched direct and derived edits. Across three model families, all policies repair direct cases, but derived cases clearly separate them. At the primary budget, a contiguous edit-local window recovers at least 0.94 of the post-edit answer margin and substantially outperforms attention-based, KV-deviation, and structural selectors. Mechanistic analysis shows that position sets effective under clean-state transplantation can fail under actual recomputation because scattered positions inherit surrounding staleness. The edit-local advantage also depends on adjacency and largely disappears when the answer-bearing text moves downstream. Because answer-relevant edits almost always corrupt model behavior, failure severity is difficult to predict, and repair is 13-21 times faster than full re-prefill, our results support unconditional edit-local repair when the dependent text remains adjacent to the edit.

Mingyang Mao, Wyatt Mackey, Xiaomin Lin

University of South Florida, Electrical and Computer Engineering · DEVCOM Army Research Laboratory

Retrieval-Augmented Generation KV Caching KV-Cache Management KV-Cache Reuse

Sep 15, 2026cs.AI

JustFit: Just-in-Time State Management for Local LLM Serving

Local agents need memory for model execution and working history. We present JustFit, an MLX runtime that coordinates their overlapping allocations: KVExec executes and checkpoints four-bit KV with bounded workspace, PhaseSwap loads phase-dependent components, and StateTrans preserves history across execution modes. With Qwen3.8-27B MXFP4 on a 24 GiB M4 Pro MacBook, JustFit reaches 327,680 retained positions across two requests, 10.67 times the evaluated baseline's 30,720-position single-request record. One request completes the full 262,144-position native window at median 5.986 tokens/s. Each shape completes 16,384 outputs per request in three fresh processes: B1 uses one cold build and two prefix extensions; B2 uses three ordered prefix extensions (Section 4). Image encoding can proceed while preserving a live 196,608-input text request. A controlled, repetitive 32K+6K workload reaches median 18.284 tokens/s at 15,626 MiB; a separate AIME 2026 evaluation scores 29/30. Coordinating execution and state lifetimes makes longer histories feasible on personal hardware.

Yuhua Chen

LLM Serving On-Device Language Model Inference KV Caching KV-Cache Management Memory-Efficient Inference LLM Agent Serving+1

Sep 15, 2026cs.LG

Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches

When agentic sessions run to a million tokens with many sessions resident at once, the KV cache and the index that ranks it live in host memory, and the scan that ranks all n keys for a top-k step becomes the traffic that bounds decoding. We present Fathom, a key scan in which each query decides how many bits of each key channel to read. The 4-bit K cache is stored channel-major as bit planes, so a prefix of t planes is exactly the channel's t-bit quantizer, and the query spends its bit budget by reverse water-filling over the variance-weighted importance of its channels. At one million tokens on Qwen3-8B a decode step is 1.67x faster in GPU time than with the 136-bit scans of Double Sparsity, Loki and SparQ r=32, and in the same GPU time as SparQ's 68-bit read (r=16) Fathom reads 18% fewer bytes with lower attention error on six of seven model and context settings. On RULER-style tasks every per-token scan matches exact top-k decoding, and on real coding-agent sessions Fathom reaches the step agreement of the most accurate 136-bit scan at 92 bits. The store is the 4-bit K copy a quantized serving stack already holds, and the method is not faster when the index is resident in GPU memory.

Vivek Kalyanarangan

KV-Cache Offloading KV Caching LLM Inference Acceleration Sparse Attention

Sep 15, 2026cs.CL

Where Should a Document Live: Context, Representations, or Parameters?

To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the context window as documents, encoded into the model's parameters, or injected as latent representations. However, each of these methods comes with different efficiency, cost, and performance trade-offs, with no single winner. We present a controlled comparison of representation-based (KV-cache based) and parametric (fine-tuning-based) adaptation methods on five knowledge-intensive benchmarks. We show that in the oracle setting, Cartridges (KV) are the most accurate injection method at nearly every storage budget, outperforming parametric methods by 10 points. Compaction (KV) matches Cartridges only at low compression rates, lagging behind the parametric methods by 10 points at rates higher than

50\times

. In the more realistic multi-document retrieval scenario, Cartridges are the only method that matches in-context learning (ICL), leading the parametric methods by 29 points and Compaction by 15 points. Nonetheless, Cartridges are also the only method, besides full fine-tuning and large MLP adapters, that suffers from catastrophic forgetting, i.e., a 6% performance degradation on control benchmarks, with 13% in coding.

Nathanaël Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias +1

Amazon AGI

Memory-Augmented Language Models Knowledge Augmentation for Language Models KV Caching LLM Fine-Tuning Retrieval-Augmented ICL

Sep 15, 2026cs.AI

Shared-Prefix KV Reuse Across Standard LoRA Adapters: Quality and Serving Tradeoffs

A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefills that shared context once per specialist. We study a narrow, practical question: for already-trained standard LoRA adapters -- not adapters retrained for cache compatibility -- how much task quality is preserved if the backbone's prefill KV cache is computed once and reused across specialists, and what does that buy in serving cost? On a Qwen3-1.7B backbone with two adapters (extractive QA on HotpotQA, arithmetic reasoning on GSM8K), we sweep the boundary at which the specialist takes over from the reused base cache and measure paired quality differences and serving cost. Full-prefix reuse had the lowest prefill cost and a small quality difference on held-out GSM8K (Delta = -4.6 EM at a 160-token budget; -3.0 at 320 tokens; -0.8 under a second training seed -- all favoring native, only the first excluding zero, and the magnitude not consistent). Partial recomputation provided no demonstrated advantage. Neither quality equivalence nor a general boundary-selection rule is established. We also report a closed-form ridge KV translator that did not beat direct reuse, and specialist-dependence contrasts whose intervals all include zero. The measured serving benefit is warm-cache time-to-first-token, which grows with context (~16x at 8K); two-branch peak memory was only 12% lower and, on inspection, the prefix was never physically shared across branches -- this implementation reuses KV values but copies their storage, so shared-cache memory savings are not achieved.

Dushyant Rajput

AltSlate Labs LLP

LLM Inference Efficiency LLM Serving KV Caching Prefix Caching KV-Cache Reuse

Sep 15, 2026cs.LG

Divergence Timing and Cumulative Disagreement under KV-Cache Eviction

KV-cache eviction perturbs the conditional token distributions governing autoregressive generation. We investigate how first-divergence timing and subsequent token mismatch determine cumulative disagreement. We derive an exact decomposition under a specified stepwise maximal coupling: the expected mismatch fraction equals a first-mismatch contribution plus post-divergence exposure multiplied by its mismatch rate. An explicit construction over unrestricted autoregressive kernel pairs realizes the sharp interval of risks compatible with a finite divergence-aligned observation window. Residual-branch conditional Monte Carlo provides unbiased joint estimates of occurrence, occupation, and window/tail contributions, with per-replicate variance dominance for total token loss. Complete trajectories from Meta-Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct show that SnapKV at 50% retention enters divergence later and less often than SnapKV-512 or recent-token retention with the same 50% prompt-cache budget, while post-divergence total variation (TV) remains high. In an exploratory analysis of 288 documents, post-divergence exposure accounts for 85-90% of four aggregate mismatch gaps. On 288 independent documents at 90% retention, prespecified comparisons show higher branch-aligned TV in the late than in the early window in both models.

Xinyue Luo, Fei Yu

Wealth AI Lab, Ant Group

KV Caching KV-Cache Eviction Distribution Matching Autoregressive Generation

Sep 14, 2026cs.AI

T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning With Dynamic Routing

Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across multiple iterations, achieving parameter efficiency without sacrificing representational power. Besides, looped Transformers perform inference directly in the latent space (latent reasoning) to reduce the number of tokens consumed during inference, thereby achieving improved sample efficiency. However, these models typically apply a fixed recursion depth uniformly to every token, leading to suboptimal compute allocation and leaving significant efficiency gains on the table. In this work, we propose \textbf{dynamic token-choice routing} for looped transformers, enabling each token to adaptively determine its own number of loop iterations based on its hidden state. We use a dynamic router to decide whether a token should continue recursing or exit early, allowing simple tokens to bypass unnecessary computation while hard tokens receive deeper processing. To ensure that this adaptive mechanism does not compromise decoding efficiency, we further introduce recursion-wise KV caching, which maintains an independent key-value cache for each recursion loop. This design ensures that tokens at different depths only attend to their corresponding cached states, effectively eliminating redundant computations for exited tokens and enabling fast autoregressive decoding. Extensive experiments show that T-LoopFormer reaches the sota performance under the same parameters on PPL and 10 zero-shot reasoning tasks, even surpassing the base model at 24x FLOPs and our model could reach the lowest inference latency, which validate the effectiveness of token-choice router and recursion-wise KV cache. Code: https://github.com/YuMingQian1234/T-LoopFormer.

Mingqian Yu, Wenpeng Zhang, Peilin Zhao

Institute of Automation Chinese Academy of Sciences Beijing, China · Independent Reasearcher · School of Artificial Intelligence Shanghai Jiao Tong University Shanghai, China

KV Caching Recurrent Transformers LLM Inference Acceleration Adaptive Computation Latent Reasoning

Sep 14, 2026cs.DC

Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance Boundaries

Shared host-memory caching can avoid repeated prefill when a request moves between inference replicas. Its usefulness depends on both correct state transfer and lost prefix locality. We study two single-GPU 27B vLLM replicas sharing a 256 GiB LMCache pool. After adopting an existing packed-page patch, we isolate a raw-pointer fallback that omits the dependency on the current CUDA stream. Controlled byte tests fail under an imposed delay and pass when the dependency is restored; the existing mixed allocator provides a working deployment path. Full-pool allocation checks and service regression complete the validation. A four-block OFF-ON-ON-OFF comparison contains 768 measured requests within two block pairs. Median cross-replica time to first content token falls from 31.715 to 0.605 seconds at 128k input and from 92.047 to 0.790 seconds at 256k. Six-turn synthetic sessions alternating replicas improve by approximately 35% and 45% at initial contexts of 32k and 128k, while fixed placement shows little benefit. This engineering case study identifies practical validation steps and the locality conditions in which shared caching pays off.

Frank Li

UNSW Sydney

KV Caching KV-Cache Management LLM Inference Acceleration Prefix Caching KV-Cache Reuse

Sep 14, 2026cs.CV

Pixel Decodability Is Not a Compression Signal: Causally Evaluating Importance Proxies for Visual KV-Cache Eviction

Vision-language models retain a substantial amount of pixel-decodable visual content in their visual key-value cache. We show, in our setting, that this retention is task-inert: across our preregistered tests, how much a unit retains never positively tracks whether the computation that answers the question causally relies on it. We measure retention with a learned pixel-inversion decoder and causal use with single-super-patch KV ablation, the teacher-forced drop in gold-answer log-probability, and relate the two within images under a preregistered, sign-calibrated, held-out design. Retention is decoupled from attention and, in a well-powered null, from causal utilization. Utilization is not inert to every proxy: attention weakly but significantly tracks it, the only signal we find that does and the design's positive control. We characterize pixel-decodable retention as an informational axis of the visual KV cache, orthogonal to the functional one. How much task-inert content a cache holds differs by architecture in our model pair: the encoder-free model retains 2.7 times more than the encoder-based one. The engineering consequence is a controlled negative result. At super-patch granularity, deconfounded pixel-decodable retention ranks KV eviction no better than random; at token granularity it acquires only a weak inverse-importance signal at larger budgets, dominated at every budget by attention magnitude. In our setting, pixel-decodable reconstructability is not a competitive KV-compression signal at any granularity we test.

Chenyu Zhou, Qiliang Jiang, Shuning Wu +1

School of Engineering, Institute of Science Tokyo, Japan · College of Control Science and Engineering, Zhejiang University, China · Department of Electrical and Computer Engineering, National University of Singapore

KV Caching KV-Cache Eviction KV-Cache Management VLM Interpretability KV-Cache Compression KV-Cache Pruning

Sep 14, 2026cs.LG

AgentKV: Phase-Aware KV Eviction for Agentic LLMs

Agentic serving can consume orders of magnitude more tokens than chatbot workloads, stressing both KV-cache capacity and decode-time bandwidth. Most KV-eviction methods score cached keys against representative queries drawn from the most recent tokens, assuming future attention resembles recent attention. We show that agentic generation violates this assumption: future queries form a mixture over think, act, tool, and others phases, and principal-angle analysis shows these components occupy measurably different query subspaces, so recency representatives systematically undervalue keys that upcoming phases will need. We propose AGENTKV, which maintains a small query buffer per phase and scores cached keys against their union. We further implement AGENTKV in a persistent multi-turn serving path that carries compressed KV state across turns and compacts retained KV pages online. Across two models, six task domains, and three KV budgets each, AGENTKV improves task score by 5.5 points on average over R-KV and 5.3 over Tri-attention. Relative to upstream full-KV SGLang, AGENTKV improves output-token throughput by up to 1.80x. Code: https://github.com/LiuTaowen-Tony/agentkv.

Taowen Tony Liu, Jeffrey T. H. Wong, Can Xiao +3

Imperial College London, London, United Kingdom · Columbia University, New York, NY, USA

KV Caching KV-Cache Eviction LLM Inference Acceleration LLM Agent Serving LLM Agents

Sep 11, 2026cs.CL

K/V-Cache Interventions Dissociate Representation Alignment from Persona Expression in Decoder-Only Language Models

We study K/V-cache interventions -- transplanting a target-conditioned K/V trajectory into a source-persona generation -- as a structured surface for persona control in decoder-only language models. Across 13 intervention configurations applied to Llama-3.1-8B for a fixed source-to-target persona pair, we report two consistent dissociations between representation-level alignment and behavioral expression, plus a common failure under position perturbations. First, all layer-band K/V replacements (early, mid, late) achieve strong local V-space alignment (V-gap 0.91, 0.89, 0.84), but only mid-layer replacement (layers 9-20) combines substantial target-marker expression with preserved lexical diversity. Second, full and mid-layer replacement induce comparable alignment (V-gap 0.94 vs. 0.89) yet produce different lexical-diversity profiles (TTR 0.65 vs. 0.77). Third, position perturbations (lag and shuffle) apply distinct operations yet uniformly suppress target-persona expression -- a common behavioral failure rather than a strict dissociation. Representation-level similarity metrics alone are thus not sufficient predictors of downstream persona expression in the regimes we study; the K/V cache emerges as a controllable but structurally constrained intervention surface. Because the transplanted trajectory carries the target's own generated token history, we characterize the intervention as trajectory-level transplantation rather than isolated persona-representation injection; a same-token-sequence control, decoding an identical token sequence under source vs. target conditioning, reproduces the sign and layer localization of the L28 representational shift, indicating the shift is not explained solely by imported token history. These findings characterize representation-behavior dissociation in a high-signal setting rather than establishing universality across models or persona pairs.

Yu Sun, Mengyin Lu, Cong Feng +2

LinkedIn

KV Caching Decoder-Only Language Models Personality Modeling in Language Models Causal Interventions in Language Models Representation Geometry in Language Models

Sep 11, 2026cs.CV

OmniKVQuant: KV Cache Quantization for Omni-LLMs

As Omni-modal large language models (Omni-LLMs) take in audio, video and text together, their KV cache memory cost grows. KV cache quantization is the de facto approach in text-only LLMs, but its application to Omni-LLMs remains unexplored. In this paper, we analyze how TurboQuant, a representative rotation-based KV cache quantization method, behaves on multimodal caches and identify two critical issues: temporal key drift and heterogeneous value geometry. To address these, we propose OmniKVQuant, a training-free framework that (i) sets the key quantization range over each short window of the input stream; and (ii) rotates values separately per modality. On Qwen2.5-Omni and Qwen3-Omni, OmniKVQuant enables 2-bit KV caches while substantially preserving performance across seven audio-visual benchmarks. We further provide a fused Triton decode kernel that unpacks the 2-bit cache during attention, so no dense FP16 cache is ever built. Code: https://github.com/kaistmm/OmniKVQuant

Suho Yoo, Hyunjong Ok, Jongmin Choi +2

KAIST · POSTECH

Efficient Multimodal Inference KV Caching Multimodal Large Language Models LLM Inference Acceleration KV-Cache Quantization Post-Training Quantization

Sep 11, 2026cs.DC

Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs

Prefix caching can reduce the time to first token (TTFT) of long-context LLM requests by reusing previously computed key-value (KV) states, but for short prefixes or fast GPUs, recomputation can be faster than loading from an external cache. We characterize this tradeoff in vLLM across GPU, CPU, and NVMe tiers using synthetic workloads, long-context benchmarks, production traces, and find that cache performance depends on transfer granularity, intermediate memory use, and when transfers enter the request schedule, not only on device bandwidth. These findings motivate py-kvcache, a vLLM KV Offload connector with asynchronous direct I/O, bounded shared staging, and scheduler-aware preloading, which starts disk reads while requests are still waiting, overlapping with compute. At 80k tokens, py-kvcache loading from disk is 2.0x faster than LMCache, with preloading contributing 1.34x. With GPU, CPU, and disk caching enabled, it is 1.23x faster than LMCache and within approximately 4% of the native vLLM KV Offload implementation. LongBench and SCBench show that these benefits extend to irregular prefix chains and multi-turn workloads. Bailian trace replays improve TTFT on a weaker GPU, but on an H100 the average request falls below the break-even point and GPU memory alone retains enough prefixes. External KV caching should therefore be treated as a setup specific admission decision. The py-kvcacheimplementation is available at: https://github.com/atlarge-research/py-kvcache.

Joseph Kanichai, Tiziano De Matteis, Animesh Trivedi

Vrije Universiteit Amsterdam Amsterdam, the Netherlands · IBM Research Zurich Zurich, Switzerland

KV-Cache Offloading KV Caching LLM Inference Scheduling LLM Inference Acceleration Prefix Caching

Sep 9, 2026cs.DC

Composable CXL Memory as a Kubernetes-Native Shared Memory for LLM Serving

We present a Kubernetes Dynamic Resource Allocation (DRA) driver that makes composable CXL memory a schedulable cluster resource, and evaluate the resulting shared-memory tier for cross-node KV-cache reuse in LLM serving. The driver composes CXL regions on demand, materializes them as DAX devices on each participating host, and injects them into pods under a single Container Device Interface (CDI) name so that pods on different nodes access the same physical region. A shared-memory connector for vLLM/llm-d uses that region as a KV-cache tier with a slot directory embedded inside the shared medium, which eliminates the need for an external metadata service. On a two-node cluster with a 512,GiB CXL appliance and Qwen2.5-7B-Instruct, cross-node prefix reuse reduces TTFT by 5.5

\times

--36.6

\times

at an external hit rate of 95.4--99.5,%, while node-local tiers (GPU prefix caching, CPU-DRAM offload) fall back to full recompute. The sharing gap, defined as the latency ratio between cross-node and same-node reuse, is 1--4%, indicating that cross-node reuse incurs little additional latency relative to same-node reuse on our testbed. Both replicas run full engines; the study demonstrates memory disaggregation rather than prefill/decode disaggregation. We report this as a feasibility study rather than a performance evaluation.

Hongjian Fan, Kevin Zhang, David Habinsky +1

Research Group, Seagate Technology, LLC

LLM Inference Efficiency KV Caching KV-Cache Reuse Distributed Inference

Sep 9, 2026cs.CL

KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

Reusing key-value (KV) caches speeds up LLM inference by avoiding repeated computation on shared text. Standard prefix caching reuses a KV cache only when the LLM is the same and all preceding text is identical, but real workloads often break both conditions: RAG systems place different documents before the same one, agents with different system prompts read the same file or tool output, multi-agent workflows use specialized LLMs on shared material, and an updated model reads documents cached by its previous version. Because KV caches depend on both the preceding text and the model weights, direct reuse can reduce answer quality. Many methods repair or compress the reused cache, but each paper uses its own tasks, models, and cost measures, and existing benchmarks mainly test long-context processing or reuse of an unchanged prefix. We introduce KVShareArena, a benchmark and open evaluation framework for comparing them under the same conditions. KVShareArena has (1) reuse tests on 2,150 questions from three QA datasets, where the preceding text, the cache-writing LLM, or both change while the answering LLM and input stay fixed; (2) five dense and mixture-of-experts LLMs (4B-30B) and six LLM pairs where one version of an LLM reads caches written by another, for 33 model-dataset settings; (3) 11 repair and compression methods from six method classes; (4) four evaluation perspectives: answer quality, prefill computation, KV-cache memory, and latency; and (5) a common interface for adding new methods and an interactive leaderboard. Experiments yield two findings. First, both the quality loss from reuse and which repairs help depend on the LLM, even between two 8B models. Second, most repairs keep their quality when another LLM version wrote the cache, but a trained repair adapter loses quality in 12 of 18 pair-dataset tests. Code and data: https://github.com/xishi404/KVShare-Arena

Xi Shi, Mengxin Zheng, Qian Lou

University of Central Florida

KV Caching LLM Inference Acceleration Prefix Caching KV-Cache Reuse

Sep 9, 2026cs.LG

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

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.

Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi

Kioxia Corporation

Retrieval-Augmented Generation KV Caching Long-Context Language Model Inference KV-Cache Management KV-Cache Reuse

Sep 8, 2026cs.AR

Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction

The KV cache is a primary bottleneck for Transformer decoding: its memory footprint and cache-read traffic grow with sequence length. Grouped-query attention (GQA) reduces this cost by sharing key-value heads, but still stores both a key and a value at every step. We introduce Grouped Value Attention (GVA), which stores grouped values and reconstructs content keys with a learned linear map. At inference, the map can be absorbed into the query, eliminating the need to materialize content keys in the intended decode path. A small shared decoupled RoPE channel retains positional information through a separately cached positional key. For the configurations studied, this representation reduces persistent cache scalars by approximately 45-47% relative to matched GQA. At the 350M-parameter scale with 30B FineWeb-Edu tokens, the 16-dimensional positional variant reaches 44.18 average accuracy across five tasks, compared with 44.36 for GQA and 43.88 for MLA. These results demonstrate near-GQA benchmark accuracy with a more compact cache representation. To translate this compact representation into faster autoregressive inference, we have developed custom decoding kernels and are currently evaluating their end-to-end inference performance with an open-source release planned soon.

Vishesh Tripathi, Abhay Kumar, Ramsha Khan

FrontiersMind

Efficient Transformer Inference Grouped-Query Attention KV Caching Efficient Attention KV-Cache Compression

Sep 8, 2026cs.AI

BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents

KV cache is evolving from a serving optimization into an external memory substrate for long-term LLM agents. In a shared multi-user deployment, however, reusable KV blocks introduce a missing access-control question: semantic relevance alone cannot determine whether a memory block is authorized for the current physical user. We propose Bio-MemArt, a biometric-aware KV-cache memory framework for multi-user LLM agents. Bio-MemArt attaches a normalized biometric template to each stored KV memory block, filters the shared memory pool with the current user's biometric probe, and then runs the original MemArt retrieval and KV reuse pipeline only inside the authorized candidate pool. This design preserves latent-space retrieval, direct cache reuse, and decoupled position encoding while adding physical-user access control to shared KV memory. We evaluate Bio-MemArt under Owner and Non-owner query conditions on long-term dialogue QA with face and palmprint benchmarks. Across face benchmarks, the average owner and non-owner biometric success rates are 95.71% and 0.86%; across palmprint benchmarks, they are 97.60% and 2.00%. In the efficiency study, average prefill tokens drop from 18,781.96 under full-context prompting to 28.57 with Bio-MemArt, showing that biometric gating preserves the low-token operating regime of KV-cache memory.

Yanhong Qian, Xuanying He, Qingguo Meng +3

Anhui Provincial Key Laboratory of Secure Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei 230093, China

Agent Memory Privacy-Preserving Language Models KV Caching KV-Cache Management Long-Term Conversational Memory Access Control

Sep 8, 2026cs.CL

Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservation

Key-value (KV) cache eviction is essential for scaling long-context inference in Large Language Models. However, existing policies predominantly rely on empirical heuristics, lacking a rigorous characterization of token utility under the inherently nonlinear softmax attention mechanism. In this work, we rethink KV cache eviction through the lens of local information geometry, modeling the attention process as a nonlinear Gaussian communication channel. By performing a first-order Taylor expansion of the attention mapping, we derive the Jacobian Information Capacity, a novel objective that explicitly captures query relevance, softmax sensitivity, and structural diversity. Guided by this theory, we introduce Jacap, a capacity-aware eviction method that utilizes softmax-aware importance weighting and statistical leverage scores for subset selection. Extensive experiments across diverse architectures and benchmarks demonstrate that \textsc{Jacap} delivers superior performance in most scenarios, particularly in high-compression regimes.

Jiaming Yang, Chenwei Tang, Liangli Zhen +2

College of Computer Science, Sichuan University, Chengdu, China · 2Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Chengdu, China · Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR), Singapore

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

Sep 7, 2026cs.LG

MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference

Key--value (KV) cache compression is an effective way to reduce the memory overhead of large language model (LLM) inference, particularly for long-context workloads. However, existing compression methods make different trade-offs among accuracy, inference latency, and peak KV cache memory utilization, making a single fixed configuration unsuitable across different prompts and resource constraints. We introduce MetaKV, an adaptive framework that selects a KV cache compression configuration for each input prompt based on user-specified latency and peak memory budgets. MetaKV uses lightweight prediction models to estimate the end-to-end latency, peak memory, and probability of a correct response for each candidate configuration, and selects the configuration that best satisfies the latency-memory constraints while preserving accuracy. We evaluate MetaKV across ten configurations from three representative KV cache compression methods, KVQuant, H

_2

O, and RocketKV, together with an uncompressed FP16 configuration, on four datasets covering mathematics, science, commonsense reasoning, and reading comprehension. Across a wide range of latency and peak memory constraints, MetaKV consistently outperforms the best static configuration, improving constrained success rate (CSR), the fraction of prompts answered correctly while satisfying both constraints, by approximately 0.07 on average and up to 0.135. These results demonstrate the benefit of adapting KV cache compression to individual prompts and latency-memory constraints. Code is available at https://github.com/MichaelWang0505/MetaKV.git

Michael Wang, Keith Li, Roozbeh Bostandoost

Lake Washington School District · XSchool · UMass Amherst

LLM Inference Efficiency LLM Inference KV Caching KV-Cache Compression

Sep 7, 2026cs.AI

RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving

Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it removes the physical per-head cache boundary assumed by conventional head-wise reuse. We present our system, a DeepSeek-V4 realization of RedKnot's head-aware reuse principle. Each immutable document is processed offline at canonical position zero; certified Local-head contributions are retained as MLA-Off. At serving time, query-side RoPE relocation restores the document's request position, a small Global-head set and protected Local token rows are recomputed as MLA-Online, and the two paths are merged before a single shared output projection. The packed MLA latent is never split. DeepSeek-V4-Flash uses 37 reusable layers and a 56/8 Local/Global partition, giving a 75.29% analytic logical head-row ceiling; the Pro-0813 profile uses 55 layers and 112/16 heads, giving 78.89%. Frozen Flash operating points show hot-artifact TTFT speedups of 2.02-3.84x. At 256K, the archived three-dataset study reports an aggregate F1 change of +3.24 percentage points, an EM change of +4.16 points, and a 78.7-79.5% analytic major-operator arithmetic saving, while one dataset decreases by 2.81 F1 points. A separate author-reported 256K hot-artifact QPS measurement is approximately 2.0x; because its raw concurrency trace is not included in this bundle, we mark it as preliminary rather than archived evidence. We describe the factorization, position repair, token-row closure, sparse-MoE support, TP8 integration, and the measurement boundaries needed to interpret these results.

Yang Liu, Zhaokai Luo, Huayi Jin +10

Xiaohongshu Inc., China · Huawei Cloud · Shanghai Jiao Tong University +2

KV Caching LLM Inference Acceleration KV-Cache Reuse Attention Mechanisms Multi-Head Latent Attention

Sep 3, 2026cs.LG

VestigeKV: The NoPE-MLA KV Cache Carries Its Own Sparse-Attention Signal in a Vestigial Branch

A long-lived KV cache must be compressed before the queries that will read it exist. Selection by observed attention collapses there: on a NoPE-MLA model, H2O and SnapKV retrieve 0.00 and 0.33 of needles at 8x compression, because a token's importance has not yet been observed. VestigeKV instead derives a sparse attention pattern from a signal the cache already carries, occupying the sparse-attention literature's one unoccupied quadrant: training-free and query-independent. In NoPE-MLA the 64-dimensional decoupled branch is a vestige of RoPE that training repurposes into a salience channel; reading 11% of each row, it partitions the cache into an attended tier and a GPU-resident archive that no row ever leaves, reachable each step by a certified, query-adaptive trigger. Nothing is trained and cache rows are never quantized, so every quality effect attributes to selection and scheduling. On Kimi Linear 48B, retrieval holds at 1.00 under 8x and 0.96 under 32x from 8k to 65k context, with zero gap to full-row selection, and the recall tier holds 128x at 1.00 (8k). Both tiers stay on the GPU, so the win is speed, not memory: the per-step scan reads ~26% of the bytes dense attention would, and on a two-node sglang deployment the crossover sits at ~40k context, reaching 1.18x at 256k and 1.39x at 496k. The mechanism is exclusive to NoPE: the identical operator on a RoPE MLA collapses to 0.08, query-independent salience exists only without rotation, and query-universal exact merging is provably impossible under RoPE. All thresholds were frozen before their data; 20 archived verdicts and 8 closed routes accompany the paper.

WenJie Fan

Yotta Labs

KV Caching KV-Cache Management LLM Inference Acceleration Sparse Attention KV-Cache Compression Attention Mechanisms+1