KV-Cache Compression

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 71% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 171

Oct 8, 2026cs.CL

VFold: Symmetry-Aware Cross-Layer Value Cache Compression

While caching key-value (KV) states accelerates Large Language Model (LLM) decoding, this cache can dominate memory usage at long context lengths. One solution is to compress this memory by exploiting inter-layer cache similarities. However, most existing techniques necessitate architectural changes to LLMs and incur substantial overhead. In this work, we propose a symmetry-aware value cache merging strategy that reduces cache memory while avoiding both harmful performance degradation and architectural overhead during decoding. Furthermore, we show that this approach can be exploited alongside existing cache compression techniques, composing with high-ratio quantization or key cache pruning to reach compression ratios that neither method reaches alone, with minimal additional cost. Ultimately, our findings reveal a major source of underutilized capacity in the value cache, offering a simple yet highly effective direction for scaling context windows under memory constraints.

Neha Verma, Sungwon Kim, Kenton Murray +1

Johns Hopkins University · George Mason University

KV-Cache Compression

Oct 8, 2026cs.CL

Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read

Many key-value (KV) caches are compressed before anyone knows what will be asked of them: a document cached for retrieval, a prompt prefix shared across requests, the memory of a long conversation. The prevailing approach scores KV entries by rehearsal: the model rereads the context and keeps the entries it attends to, assuming that the more completely a cache rehearses its context, the better it remembers it. We show that under tight budgets this assumption backfires: rehearse everything, remember nothing. At a 3% keep ratio, rereading the whole context keeps 31.5 of 96.5 points on RULER, and on LongBench's natural-text tasks it falls below methods that rehearse nothing at all. The cause is that a cache keeps what it rehearses: rereading spreads the budget across the whole context, so the answer's own entries survive at little more than chance. Like a student before an exam, a cache remembers more by testing itself than by rereading. Two principles follow: rehearse what will be read, and rehearse as much as there is. We instantiate them as Attic-KV (Attic for short), a training-free rehearsal in which the model quizzes itself with question-answer pairs that quote the context, alongside anchor tokens in a content-adaptive amount. Changing only the rehearsal lifts three hosts that score it in three different ways: Attic alone is the best training-free method in all eight settings we test on RULER and LongBench's natural-text tasks, and plugged into the gradient-based KVgrad and the trained RestoreKV+, it raises them by up to 17.1 and 28.1 points. Its advantage grows as the budget shrinks, reaching 41.9 points over full rereading at a 3% keep ratio, and it compresses faster than rereading the whole context.

Zhiyun Shi

Nanyang Technological University Singapore

KV-Cache Compression KV-Cache Pruning

Oct 8, 2026cs.LG

Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learning

Tabular in-context learning (ICL) has emerged as a training-free and accurate paradigm for tabular prediction, but current approaches to compressing its in-context examples face an accuracy-throughput tradeoff: fixed subsets can sacrifice accuracy, while query-specific retrieval limits cache reuse and batching across queries, reducing throughput. We propose QCOC (Query-Calibrated Operator Compression), which exploits the exchangeability and repeated use of in-context examples by compiling their full KV cache once into compact memory shared across subsequent queries. Instead of retaining raw examples, QCOC clusters their states into joint-KV prototypes, preserves per-cluster multiplicities and the original example count, and calibrates prototype values against attention query vectors produced by the in-context examples through an anchored closed-form solution. Prototype compression drives the speedup, while value fitting helps preserve accuracy. On 64 held-out OpenML-CC18 datasets, QCOC achieves the highest mean accuracy among the compared compression and retrieval methods at both retained counts. Across 12 configurations on seven long tables, it ranks first among compressed methods in ten and averages 0.23 percentage points below full context. Compressing 8,192 in-context examples to 512 memory slots yields a 10.5x cache compression ratio; excluding one-time compilation, in a single-core CPU online-serving comparison over 1,000 queries, QCOC is up to 508x faster than dynamic retrieval baselines and 1.98x faster than full-context inference. These results show that QCOC enables compact-memory reuse and efficient inference across queries while retaining accuracy close to full context.

Xu Zhao, Jiaming Zhao, Bin Zhao +1

Context Compression Tabular ICL KV-Cache Compression Memory-Efficient Inference Tabular ML

Oct 8, 2026cs.LG

Read What Matters: Query-Adaptive Quantization for KV Caches

KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places. We study this mismatch using separate budgets for retained bits and bits fetched per query. ReadKV stores each key and value in a progressive code whose prefixes support different reconstruction precisions. For each query, it allocates key-channel prefixes using the query, computes attention from the reconstructed keys, and then allocates value-token prefixes using that attention. Stored entries remain unchanged. Each stage optimizes a calibrated distortion objective under a fixed budget; we prove exact allocation under diminishing refinement gains and relate these objectives to attention-output error. We also exhibit a finite-dimensional attention family where query-dependent access strictly outperforms every query-independent reader at the same read budget, even with unrestricted competing encoders and decoders. Across six base models, reading four bits on average from an eight-bit cache increases C4 perplexity by at most 0.66%, using about one quarter of the logical reads and half the retained capacity of a 16-bit cache. It is consistently more accurate than storing and fully reading four bits at the same payload-read budget. Retaining more bits than each query fetches is aimed at long-context decoding, where the cache bytes moved per step, rather than the weights, dominate cost. Long-context question answering and retrieval on two instruction-tuned models provide additional quality evidence. On the tested 8K-token, batch-one, single-layer workload on an NVIDIA A10G, a restricted eight-bit ReadKV reader with a two-bit mean payload-read budget has 39% lower latency than the tested TurboQuant codec.

Siddharth Bhandari, Lucas Gretta, Krishna Balasubramanian +1

Amazon · University of California, Berkeley

KV-Cache Quantization KV-Cache Compression Neural Network Quantization Long-Context Inference

Oct 7, 2026cs.LG

Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV Caches

Long inputs and extended generation increase the storage and access costs of the key-value (KV) cache. Low-bit quantization reduces storage and memory traffic, while query-channel pruning can further reduce key-cache reads. Rotation-based quantization redistributes the energy of key outliers across channels. To maintain computational invariance, the same orthogonal transform must be applied to queries, preserving query-key dot products. However, this rotation can disperse query energy, weakening the separation between a few large components to retain and many small ones to prune. We introduce Dual-QK, which uses paired non-orthogonal query and key transforms to address this conflict. Using calibrated query and key statistics, Dual-QK combines partial key whitening with a query-aligned basis to balance key scales for INT2 quantization and concentrate query energy for dynamic channel pruning. Channel-0 protection and bucket-relative RoPE support low-bit accuracy over long contexts. Experiments on four models across five generative benchmarks and long-context retrieval tasks show improved accuracy over OSCAR on most tasks at 40% query-channel sparsity. At a 128K context, Dual-QK provides

6.8\times

KV-cache compression and an estimated

8.3\times

reduction in KV read volume relative to unpruned BF16. Under the evaluated configurations, our SGLang implementation achieves up to

3.75\times

the decoding throughput of unpruned BF16.

Sunjoo Whang, Jungjun Oh, Minsung Kim +5

KAIST · GIST · Google Research

KV-Cache Compression KV-Cache Quantization KV-Cache Pruning Low-Bit Quantization

Oct 7, 2026cs.LG

CHASE: Channel-Aligned Structure Exploitation for Geometry-Aware Model Engineering

Geometric and Spectral Alignment (GSA) characterizes trained networks through spectral concentration, physical-channel alignment, support structure, and changes in singular bases. In this paper, we propose CHASE (Channel-Aligned Structure Exploitation) to use these structures in practical model design. CHASE covers six applications across model modification, reconfiguration, and compression. CORA, COEC, and CORAM apply GSA to parameter-efficient finetuning, structured-pruning compensation, and model merging. We further develop three new methods. CAGA uses GSA to identify multi-head attention heads that can share a KV representation and constructs the shared key and value heads through geometric alignment and low-rank subspace extraction. SAKV uses GSA to determine which adjacent layers can share a low-rank KV-cache representation and the retained rank for each layer group. CAPS uses GSA spectral structure to group output neurons and selects retained input channels separately for each group. Results from CORA, COEC, and CORAM establish the effectiveness of GSA for adaptation, pruning compensation, and model merging. Experiments on CAGA show that geometric shared-head construction substantially improves MHA-to-GQA conversion, and SAKV and CAPS improve over representative baselines for KV-cache compression and structured pruning. These results show that the structures identified by GSA can be used directly to design methods for a range of model operations.

Wei Wang, Wei Jiang, Ziran Liu

Futurewei Technologies San Jose, CA 95131, USA · Shanghai Institute for Mathematics and Interdisciplinary Sciences (SIMIS) Shanghai, 200433, China

Neural Network Compression KV-Cache Compression Model Merging Neural Network Pruning Grouped-Query Attention

Oct 6, 2026cs.LG

A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention

The large KV-cache size of modern LLMs creates a barrier to efficient deployment. Recent work has explored replacing attention layers' RoPE positional embeddings with alternative decay-based mechanisms, which can then be used to prune KV-cache during inference. However, these decay functions have limited expressivity, and in practice devolve into sliding-window-like eviction patterns. In this work, we propose a unifying framework for complementary and novel decay mechanisms, capturing complex key statistics and interactions while preserving expressive RoPE embeddings and Softmax attention. The resulting Universal Attention is a highly expressive and end-to-end trainable architecture, whose composite decay mechanism acts as a natural,

\textit{adaptive}

pruning criterion, removing tokens that contribute least to attention computation. Experimentally, Universal Attention achieves state-of-the-art

10\times

compression on natural language and synthetic task data, while

\textit{improving}

downstream performance compared to both state-of-the-art baselines and unpruned oracles. It further demonstrates superior long-context generalization with unprecedented

25\times

compression at length 16k.

Davis Wertheimer, Haochen Shen, Ahan Gupta +6

IBM Research, USA · SSAIL Lab, University of Illinois Urbana-Champaign

KV-Cache Compression Transformer Attention LLM Compression KV-Cache Pruning LLM Pruning

Oct 6, 2026cs.CL

Hybrid Latent Attention for Looped Language Models

Looped language models apply the same stack of layers T times to each token, which deepens the model without adding parameters but multiplies its key-value (KV) cache by T. The larger cache limits how many sequences a GPU can decode at once and slows each decoding step, which reads the whole cache. We propose Hybrid Latent Attention (HLA), which keeps exact keys and values within a sliding window of W recent tokens and stores each older token as a compact latent that the query of each loop reads directly, without reconstructing keys and values. We uptrain HLA on Ouro looped models (T=4) with 1.4B and 2.6B parameters, keeping the pretrained weights frozen and training only the added parameters to reproduce the original attention. The cache shrinks by 10.7x per token, fitting 4.0-8.8x as many concurrent sequences per GPU, and decoding throughput improves by 2.5x at 1K-token contexts and by up to 7.4x at 16K. HLA retains over 97% of the original accuracy on math, knowledge and reasoning benchmarks, and 96-100% on long-context retrieval up to 16K tokens. After supervised fine-tuning, it performs on par with the fine-tuned original model on competition-level math.

Yuhan Chen, Siyuan Zhang, Nan Wang +2

Virginia Tech · Independent Researcher

Long-Context Language Model Inference LLM Inference Acceleration KV-Cache Compression Hybrid Attention Recursive Language Models

Oct 5, 2026cs.LG

OVAL: Output-Aware Local Page Bases for KV Cache Retrieval

Long context inference with large language models becomes increasingly expensive as attention must operate over an ever growing KV cache. Page sparse attention reduces this cost by representing each KV page compactly and retrieving only a subset for each query. Existing retrieval methods are designed to estimate attention scores or page relevance, but their objectives do not directly account for how approximation errors affect the resulting value weighted attention output. We introduce \method{}, an output aware page encoding derived from the joint structure of keys and values while preserving the key information needed for accurate retrieval. \method{} is training free and requires no additional value dependent statistics at inference time. Once constructed, its stored representation has the same size and decode time scoring cost as a key only spectral representation. Across long reasoning, long context understanding, and long generation benchmarks, \method{} consistently improves over the key only spectral baseline and performs competitively with recent KV cache compression and retrieval methods. On long reasoning benchmarks, it achieves strong avg@

k

performance across model benchmark pairs, while matching or surpassing leading baselines on several long context understanding and generation settings with modest decoding overhead. Code is available at https://github.com/Ashkan13776/oval-kv.

Ashkan Shahbazi, Chayne Thrash, Soheil Kolouri

College of Connected Computing Vanderbilt University Nashville, TN, USA

Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention KV-Cache Compression

Oct 5, 2026cs.CL

Behavior-Preserving KV Cache Compression

KV caches are a major bottleneck in long-context inference and long-form generation with large language models. Existing training-free eviction policies largely rely on proxy importance signals, such as attention mass, to decide which past tokens to retain. We argue that cache compression should instead preserve the predictive behavior of the full-cache model, retaining entries whose removal would substantially change the model's output distribution. We propose Behavior-Preserving KV Cache Compression, a training-free framework that scores candidate evictions by estimating the compressed-cache logits induced by their removal and evaluating the resulting KL to the full-cache next-token distribution. Using pre-eviction forward statistics, the method avoids running separate masked forward passes for each candidate. Across diverse architectures and both prefill-time and generation-time compression, our method delivers substantial gains in downstream task quality over lightweight attention-based heuristics at matched retained-KV budgets, with the largest gains under aggressive compression. It achieves these gains with additional compression-time computation while retaining an end-to-end speedup over full-cache inference in our evaluated settings.

Doo Hwan Hwang, Junyoung Jang, Junho Na +2

Kim Jaechul Graduate School of AI, KAIST, Daejeon, Republic of Korea · KT Corporation, Seoul, Republic of Korea

KV-Cache Eviction LLM Inference Acceleration KV-Cache Compression

Oct 5, 2026cs.CL

DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression

Long-context large language models (LLMs) have demonstrated strong capabilities across a wide range of tasks, but the growing KV cache introduces substantial memory and inference overhead. Existing one-shot KV cache compression methods typically commit to irreversible eviction immediately after prefill, before any signal from actual generation becomes available. Our quantitative analysis shows that early queries from the actual generation stage provide attention signals that are more consistent with subsequent decode attention, with the largest single-step gain occurring at the prefill-decode boundary. Based on this observation, we propose DeferKV, which moves the eviction decision from the end of prefill to the first real decoding step and temporally combines prompt-side and decode-side observations, thereby better aligning KV importance estimation with subsequent generation requirements. DeferKV requires no additional training, draft model, or future-query prediction module, making it simple and easy to deploy. Experiments on LongBench, RULER, and Needle-in-a-Haystack demonstrate that DeferKV consistently improves model performance under KV cache compression while maintaining low inference latency.

Zhe Wang, Jiakai Li, Yujia Sun +2

University of Electronic Science and Technology of China, Chengdu, China · Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province, Chengdu, China

Long-Context Language Model Inference KV-Cache Eviction KV-Cache Compression

Oct 5, 2026cs.LG

The Optimization Landscape of Learning Compacted Context Models

Many works approach continual learning through the lens of infinite context windows. As an agent puts more observation into context (concretely the KV cache), compacting said context is akin to direct memory manipulation, without affecting the base model's weights. Many works pose KV compaction as an optimization problem: learn a smaller set of KV vectors that matches the behavior of the full KV cache. While this preserves base model behavior, optimizing through a frozen base model results in a highly nontrivial optimization problem with a brittle and flat loss landscape. In this paper, we characterize what makes these optimization problems difficult and demonstrate that a heavily simplified Perceiver-based architecture not only matches performance of a full Perceiver transformer in continuous context compaction, but outperforms baselines on compaction utility. Results are presented on MCQ tasks across Finance, Legal, Gutenberg, and Code.

Thomas Villeneuve, Alex Sandomirsky, Charles O'Neill +2

Base Labs

LLM Compression KV-Cache Compression

Oct 5, 2026cs.CL

Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning

Reasoning models write most of their KV cache while decoding long chains of thought (CoT), so the cache has to be compressed online under a fixed memory budget. Decode-time methods mostly decide which tokens to evict. We ask how a fixed byte budget should be split between the number of cached tokens and their precision. BreadthKV spends the bytes on more tokens at low precision, combining quantization with eviction, and picks the bit-width for each model and budget with a 60-problem end-to-end calibration, since offline attention error does not predict it reliably. On three reasoning models and four math and science benchmarks, it scores above eviction alone in 17 of 18 settings and produces shorter outputs. Much of what eviction loses comes from derailed runs, which keep reasoning until the length cap without reaching an answer. On Qwen3-8B at our tightest budget, eviction sends 91% of AIME samples to the cap and BreadthKV 40%. Under the same protocol, BreadthKV is statistically indistinguishable from a joint rate-distortion allocator (RDKV) that uses 27% more KV memory-time, and it outperforms our re-implementation of ThinKV.

Runguo Li

University of Illinois Urbana-Champaign

CoT Reasoning KV-Cache Eviction Memory-Efficient Inference KV-Cache Compression KV-Cache Quantization

Sep 30, 2026cs.LG

EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction

KV cache pruning reduces long-context inference memory usage by evicting less important key-value pairs. KVzip estimates importance through context reconstruction: prompting a model to repeat the context chunk by chunk. This achieves strong compression quality at the cost of additional forward passes. Learned approximations reduce this cost but require model-specific training. We analyze how KVzip identifies important cached information and show how to approximate its reconstruction scores using information already computed during prefill. These findings motivate EchoPress, a training-free method that approximates reconstruction attention using queries and keys from standard prefill. For each request, it reconstructs only the first chunk to calibrate importance scores for the remaining context. Experiments on LongBench and RULER with Qwen3-8B and Llama-3.1-8B-Instruct show that EchoPress matches KVzip in task accuracy across eviction ratios from 50% to 90%, while reducing compression overhead by a factor of 1.7-19.6 and total prefill time by a factor of up to 2.9. Code is available at https://github.com/ljwljwljwljw/kvpress/tree/echo-press.

Jiawei Lin, Saibo Geng, Thomas Bourgeat

EPFL

KV-Cache Management LLM Inference Acceleration KV-Cache Compression KV-Cache Pruning

Sep 30, 2026cs.LG

PatchKV: Weight-Space Compensation of KV Cache

Long-context inference with Large Language Models (LLMs) is bottlenecked by the linearly growing memory of the key-value (KV) cache. Existing compression methods reduce the cache through token eviction or approximation, but degrade sharply at aggressive compression budgets. We propose PatchKV, a training-free framework that compensates KV cache compression methods by carrying part of the context in the model's weights. PatchKV pairs an off-the-shelf compressed KV cache with a context-specific weight patch, which is computed once at context-loading time and served for downstream queries for the context. The weight patch is derived in closed form via ridge regression, by aligning the block-wise activations of context-derived reference query tokens under the full cache and the compressed cache. Once merged into the model, the patch leaves the forward graph and per-query inference cost unchanged in the single-context, multi-query setting. Across long-context QA (SCBench with up to 170K tokens, SQuAD, NIAH) and math (GSM8K) benchmarks on three model architectures, PatchKV consistently improves cache compression methods, suggesting an alternative direction to compensate them at aggressive budgets.

Chanryeol Lee, Chanhyuk Lee, Yeonwoo Choi +2

KAIST

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

Sep 30, 2026cs.LG

SparseEngine: Sparse-First Inference Engine

Long-context LLM agents accumulate interaction histories that strain KV-cache memory and attention computation. Although sparse attention reduces these costs, heterogeneous cache representations and workflows hinder integration with existing inference engines, while prior sparse-serving abstractions support only specific layouts or workflows. We present SparseEngine, a ground-up, sparse-first inference engine whose shared lifecycle contract lets each method control its KV representation and computation while coordinating state transitions with common serving infrastructure. SparseEngine supports 15 methods across four categories and enables cross-request state management through Chain Cache, which resumes KV-eviction methods from retained history, and controllable Prefix-Cache Pruning, which removes KV from selected history regions while preserving logical-prefix matching. While maintaining method quality, SparseEngine delivers over 10x higher throughput with KV eviction, over 2.5x faster decoding at matched concurrency than vLLM, and over 2x end-to-end speedup on agent benchmarks. The code is available at https://github.com/CURRENTF/SparseEngine.

Jitai Hao, Quansheng Gu, Qiang Huang +1

LLM Inference Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention KV-Cache Compression Long-Horizon LLM Agents

Sep 29, 2026cs.AI

KV-Kaizen: Learning Context-Adaptive Cache Compression Choices

As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This impacts LLM throughput negatively, since decoding is memory-bound and decode cost grows with cache size. Recent work alleviates this bottleneck by discarding the least relevant tokens. Eviction introduces a tension, since a one-off decision to discard content may prove detrimental later. Instead, we focus on alternative choices that can lead to cache compression without evicting tokens. We achieve this by learning a selector that is able to produce, based on context, a per-layer cache configuration towards an overall compression budget. The selector operates along three axes: sharing one cache across layers (depth), caching at fewer bits (precision), or truncating the low-rank latent cache representations (rank). We call the resulting method KV-Kaizen, for the many small per-layer choices it compounds. We observe that these interventions taken independently and uniformly over all layers limit achievable compression because they degrade accuracy. Crucially, composing them locally and adaptively to the context can instead preserve accuracy while achieving large memory savings. At inference, the selector runs once, before pre-fill. In evaluations on instruction following and reasoning tasks, our selectors reach the Pareto frontier of accuracy against cache size, against learning-free and post-hoc baselines. On long-context tasks, KV-Kaizen improves on eviction and can be composed with it, reaching a 32x smaller decode-time cache on a 14B model while preserving accuracy. A 4x cache size reduction incurs no accuracy degradation from 7B parameters up, and a compressed model is more accurate than a smaller uncompressed one with the same cache size. Together, these findings support pre-training large models and compressing them only afterwards.

Joao Monteiro, Louis Béthune, Anastasiia Filippova +3

Apple

LLM Inference Acceleration Low-Rank Compression KV-Cache Compression KV-Cache Quantization

Sep 29, 2026cs.AI

ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction

Long-context large language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for long, reusable context prefixes, whose cache must serve many downstream queries. Reconstruction-based methods such as Attention Matching achieve strong downstream task performance with compact KV caches. However, iterative anchor search dominates the compaction cost of OMP-based Attention Matching. This motivates our selective amortization principle of learning a reusable anchor-selection policy across contexts while retaining context-specific reconstruction. In this work, we propose ARC-KV, a novel reconstruction-based KV cache compaction method that follows this principle. To this end, we first train a value-aware indexer to select real-key anchors in a single scoring pass. ARC-KV then applies convex-hull-constrained key merging and fits an attention-mass bias and compact values against the full cache. At inference time, ARC-KV builds the compact cache once per context using the frozen indexer and reuses it for all subsequent queries. Extensive experiments demonstrate that ARC-KV outperforms reported compaction methods in most settings across QuALITY, RULER, and LongBench on Llama-3.1-8B-Instruct. In particular, at 10% KV retention on QuALITY, ARC-KV improves accuracy from 0.6409 to 0.6474 over Attention Matching while reducing compaction time by a factor of 25.73, from 959.8 s to 37.3 s.

Zheyu Shen, Guanhua Wang, Dezhan Tu +5

University of Maryland, College Park · Meta

Long-Context Language Modeling KV-Cache Management LLM Inference Acceleration KV-Cache Compression

Sep 28, 2026cs.LG

Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression

Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer cache entries at a fixed stride. Such compression also introduces a new positional coordinate: a token's phase, or its position relative to compression-window boundaries. We uncover a systematic asymmetry in models using such compression: the same information can be easy to retrieve at one phase and difficult at another. We call this periodic variation in retrieval performance phase sensitivity. In large open-weight models with such compression, long-context retrieval accuracy can differ by up to 40 percentage points across phases, revealing periodic weak spots that average benchmark scores can conceal. To investigate this behavior, we pretrain a family of transformers from scratch across multiple KV-compression designs, reproducing phase sensitivity across the variants. Mechanistic analysis using causal interventions in these models reveals phase specialization: different attention components contribute asymmetrically to retrieving information at different source phases. We further analyze idealized retrieval models, showing how gradient flow dynamics may favor sharp phase specialization. Evaluating models with chunked KV-cache compression thus requires measuring across compression phases: high average accuracy can coexist with systematic positional failures.

Xingyu Zhu, Pu, Yi +6

Luke · ByteDance Seed · University of California, Berkeley

Long-Context Retrieval KV-Cache Compression Sensitivity Analysis

Sep 28, 2026cs.LG

Cartridges++: KV Cache Compression without Off-Context Derailment

Serving long documents to a Large Language Model (LLM) repeatedly is expensive: computations grow with context length, and the memory footprint of the key-value (KV) cache balloons. Compressed KV (CKV) representations aim to mimic the cache of a document and are typically computed once and for all, ahead of inference time. Methods to obtain CKVs range from drop mechanisms that reduce their number of columns, to learned approaches. Among the latter, Cartridges have emerged as a leading compression method, learning compact KV representations through distillation on relevant Q/A pairs. While existing evaluations focus primarily on whether Cartridges and other CKVs yield approximately similar responses to document-related, on-context queries, we investigate the crucial deployment question of whether they can handle off-context queries, something the native KV representation is particularly good at, thanks to the mechanics of attention. We observe a fundamental trade-off: while Cartridges perform better for on-context queries, heuristic-variants preserve better the original LLM's ability to operate off-context. We measure this through their capability to avoid context contamination in their response, retain general knowledge, and follow instructions. We propose Cartridges++, simple modifications to cartridges that retain off-context abilities at small or negligible cost. The router variant decides at inference time whether the query should use the learned long-context memory, while the data-mixing variant allocates a small fraction of training Q/As to queries outside the reference long document. Our study shows that assessing CKVs on document utility alone can mask substantial degradation in broader model capabilities, yet those issues can be fixed with benign changes to CKV inference or training.

Sonia Laguna, Joao Monteiro, Marco Cuturi +2

Apple

Memory-Augmented Language Models Long-Context Language Model Inference KV-Cache Compression

Sep 27, 2026cs.LG

Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving

Large language model (LLM) serving is increasingly constrained by the GPU memory consumed by key-value (KV) caches. Existing compression, eviction, and offloading techniques alleviate this pressure, but serving runtimes typically treat only the configured target KV representation as execution-ready. Under memory pressure, this target-only contract can turn KV shortage into request stalls and preemptions. We present ElasticKV, a mixed-fidelity KV runtime built on the observation that target fidelity need not gate execution. ElasticKV introduces a compact intermediate KV state, making fidelity a runtime-managed execution property. To realize this state in a paged serving runtime, ElasticKV combines (i) a pair-structured layout that turns fidelity reduction into reusable GPU capacity, (ii) a dual-mode attention backend that directly consumes the compact state while preserving the native target-only path, and (iii) pressure-aware fidelity management that adapts KV fidelity to memory pressure. Our extensive evaluation across diverse workloads, model families and scales, and GPU platforms demonstrates the effectiveness and generality of ElasticKV. Under high concurrency, ElasticKV achieves 3.8-4.0

\times

lower time-to-first-token (TTFT) and 9.1

\times

lower P90 TTFT than vLLM while preserving generation quality.

Jiantong Jiang, Yue Yang, Peiyu Yang +1

University of Melbourne · Maincode

LLM Serving KV-Cache Management LLM Inference Acceleration KV-Cache Compression KV-Cache Quantization

Sep 27, 2026cs.LG

When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression

Training-free KV-cache compression methods such as SnapKV, H2O, and PyramidKV evict tokens at the end of prefill, aiming to preserve the attention mass that future queries are expected to use -optimizing what to keep. We show that this objective fails in two distinct ways. (1) Compensation: restoring the evicted attention mass can recover the attention-level target without recovering task quality. (2) Selection: covering more of the true decode-query mass can hurt quality when the recovered mass is fragmented rather than concentrated in coherent spans. These failures share a common cause: eviction occurs before the queries that determine the answer trajectory exist. We propose Draft-Guided Eviction (DGE), which defers eviction until after drafting the first k=2 answer tokens using the full cache - just one decode step beyond prefill. Because the draft is generated from the answer's own prefix, no cache entries are discarded before this trajectory signal becomes available. The per-head cache budget remains unchanged, and DGE can be applied directly to SnapKV, PyramidKV, H2O, and StreamingLLM without modifying their eviction scores. Unlike extra-pass methods, DGE changes when eviction occurs rather than what cache entries are selected. Extensive experiments demonstrate that DGE outperforms prior methods at every evaluated budget on five of six instruct-tuned backbones, achieving 44.2 on LongBench, nearly matching FullKV at 44.3. The timing-only control DGE-W achieves the same score, demonstrating that the gain comes from when eviction occurs rather than what is selected - an effect we term trajectory anchoring.

Haeyong Kang, Chang D. Yoo

Duksung Women’s University · KAIST

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

Sep 24, 2026cs.CL

MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression

Many-shot in-context learning (ICL) enables large language models (LLMs) to adapt to complex tasks by conditioning on thousands of demonstration examples, but this paradigm shifts the inference efficiency bottleneck to the key-value (KV) cache memory. Due to the linear scaling behavior of the KV cache, storing these intermediate tensors has become a paramount challenge for both online serving and on-device deployment. To address this issue, we propose a novel compression framework, termed MILO, that exploits the low-rank redundancy inherent in many-shot contexts. Specifically, MILO features a block-wise low-rank compression strategy that compresses the KV cache at the block granularity, where each block contains multiple many-shot examples. Furthermore, to handle the heterogeneous context density across different blocks, MILO dynamically allocates rank budgets based on the information entropy, preserving the fidelity of critical blocks while aggressively compressing redundant ones. Experimental results on Qwen2.5 models demonstrate that our method achieves up to 50% reduction in KV cache memory and 1.8x throughput improvement, with negligible performance degradation on classification and reasoning benchmarks, significantly outperforming prior baselines.

Youpeng Zhao, Tian Tan, Liqian Peng +2

Google · University of Central Florida

Memory-Efficient Inference LLM Inference Acceleration In-Context Learning Low-Rank Compression KV-Cache Compression

Sep 23, 2026math.NA

Tensor Decomposition of Transformer Key-Value Caches: Spectral Structure and Format Comparison

The key-value (KV) cache of autoregressive transformers can be viewed as a fourth-order tensor spanning attention heads, tokens, features, and grouped layers. We measure the singular-value spectra of all four mode unfoldings on Mistral-7B-v0.3 and LLaMA-2-13B and compare four standard tensor decompositions: Tucker, CP, tensor train, and t-SVD, at matched storage. The spectra partition the four axes into two classes. The token and feature modes carry low-rank structure, particularly for keys. The head and layer modes are nearly full-rank and resist compression at any practical error level. Among the four decompositions, Tucker achieves the lowest reconstruction error at every compression ratio from

2\times

to

5\times

, because it can leave the full-rank modes untouched. Comparisons with two-dimensional unfolding baselines show that the preferred representation differs between keys and values: 2D methods achieve lower key error, while four-way Tucker achieves lower value error at matched storage. A mode-pinning theorem certifies the full-rank preservation from the measured spectra alone. Two further spectral properties affect the compressible modes without touching the full-rank ones: values reach a higher error floor than keys at every ratio, and post-RoPE keys lose

41\%

-

64\%

of their pre-RoPE compressibility on both models.

Rahul Krishnan, Volker Schulz

Universität Trier · Fachbereich IV, Mathematik, Universität Trier

Tensor Decomposition TT Decomposition KV-Cache Compression

Sep 22, 2026cs.CV

QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models

Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment bottleneck, which motivates low-bit quantization study for efficiency. Existing 2-bit KV cache quantization methods can achieve nearly lossless performance on VBench, however, when applied to video world models, we find they still cause severe temporal flickering and visual degradation. Meanwhile, deeper investigates show that Key quantization produces smaller reconstruction errors than Value, but surprisingly leads to larger output degradation. We trace this discrepancy to attention in video world models: Key perturbations can change the attention logits, and shift the temporal-spatial tokens selected by Queries. These observations motivate us to preserve attention logits and temporal-spatial token selection during KV cache quantization. To address this issue, we present QuantWM, a training-free 2-bit KV cache quantization framework for video world models. QuantWM introduces two complementary techniques to mitigate the attention shifts. Firstly, quantization-sensitivity-aware clustering (QSAC) jointly considers historical Query sensitivity and residual ranges to select INT2-friendly Key centroids, which reduces quantization errors in channels that are more critical to attention. In addition, principal-subspace attention compensation (PSAC) restores the remaining Key errors along the dominant Query subspace using low-rank projections, which provides a direct and efficient correction to stabilize attention logits. Experiments on LingBot-World-v2, HY-World 1.5, Matrix-Game-2, Longcat-Video and Causal-Forcing demonstrate that QuantWM significantly improves visual quality and temporal consistency, while outperforming existing methods across benchmarks with up to 6.20 KV cache memory compression and limited additional overhead.

Jiaqi Zhao, Xiaobin Hu, Bo Yin +3

Harbin Institute of Technology (Shenzhen), Shenzhen, China · National University of Singapore, Singapore

KV-Cache Compression KV-Cache Quantization Low-Bit Quantization Temporal Consistency in Video Generation Video World Models

Sep 22, 2026cs.CL

Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference

Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing latency, energy consumption, and GPU memory demand as context length scales. Existing soft-compression methods either lack query-guided memory selection at inference time, train without answer-targeted supervision, or couple compression tightly to a specific decoder architecture. We propose a Context-to-Answer-Aligned Memory Compression (CMC) framework, which compresses long input contexts into compact Context Memory Embeddings (CMEs) aligned to any frozen decoder's embedding space, reducing inference costs without modifying decoder weights. CMC introduces a two-tier KV cache that combines question-guided CME selection with a local context window, and trains the compressor with answer-targeted distillation from a frozen LLM. Experiments across nine encoder-decoder combinations and four QA benchmarks show that CMC consistently outperforms the baseline, achieving up to 7.3 EM and 4.0 F1 point gains on SQuAD, while reducing inference time and energy consumption by up to 20% and peak reserved GPU memory by up to 50% at 3,000 generation tokens. Ablation studies confirm that each architectural component and training objective contributes to the performance.

Md Mostafizer Rahman, Md Faizul Ibne Amin, Md Shahajada Mia +2

Lucy Family Institute for Data & Society, University of Notre Dame, IN, USA · The University of Aizu, Aizuwakamatsu, Japan · Department of Applied and Computational Mathematics and Statistics, University of Notre Dame, IN, USA

LLM Inference Efficiency Long-Context Language Model Inference Memory-Efficient Inference KV-Cache Compression Context Compression

Sep 21, 2026cs.LG

ARM: Attention with Routed-Memory for Learnable Sparse Control

Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are necessary for stable computation. Techniques such as selective token eviction and pruning have vastly mitigated these issues, but often discard core information to manage the growing cache. In this paper, we propose Attention with Routed Memory (ARM) a novel KV caching structure that introduces a fully differentiable, fixed-size memory system organized as a hierarchical router. Via a Gumbel-Softmax, ARM learns to select memory slots and perform sigmoid-gated updates that softly combine new and stored information, avoiding hard eviction and reducing information loss. By further training a policy to dynamically select varying amounts of memory at inference, ARM adapts its accesses for both simple contexts and inputs that require deeper reasoning, enabling more scalable and effective retrieval on both short- and long-contexts. Experimental results on standard commonsense and long-context reasoning benchmarks demonstrate that ARM achieves superior performance and efficiency compared to fixed KV-caching approaches, while remaining efficient and scalable in terms of both memory and generation latency.

Qiuhao Zeng, Jerry Huang, Peng Lu +7

University of Toronto, Canada · Vector Institute, Canada · RIKEN AIP, Japan +3

Memory-Augmented Language Models Long-Context Language Model Inference Memory-Efficient Inference LLM Inference Acceleration KV-Cache Compression

Sep 21, 2026cs.LG

KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation

What limits KV-cache compression at extreme bit-rates? We argue that it is not the choice of compression scheme, but how its budget is allocated across attention heads. Existing methods apply rank and bit-width uniformly, ignoring that each head has a different optimal mix of rank truncation and quantization. We show that co-optimizing rank and bit-width per head, using only standard low-rank projection and scalar quantization, dominates uniform allocation, with the largest gains at low bit-rates. Our method, KV-COBRA (Co-Optimized Bit-Rank Allocation), formalizes this as a resource-allocation problem: it balances rank-truncation loss against quantization loss within each head, then redistributes budget across heads to minimize total distortion. A fused Hadamard rotation equalizes per-channel variance, and reordering the SVD basis by attention-KL importance makes the solver query-aware. The same allocator extends to joint

K{+}V

compression. On perplexity, zero-shot, and long-context benchmarks from

0.5

to

4

bits per dimension (bpd), KV-COBRA shows the smallest accuracy degradation among evaluated methods at low bpd, with no per-token overhead.

Sihyeon Ha, Jaeho Lee, Yo-Seb Jeon

Pohang University of Science and Technology (POSTECH)

Low-Rank Compression KV-Cache Compression KV-Cache Quantization

Sep 17, 2026cs.AI

Marginal utility, matrix factorization, and the Key-Value (KV) cache: a unified information-economic framework for sovereign geo-mining inference

This paper builds a theoretical bridge between the economic notion of marginal utility and two machine-learning constructs, matrix factorization and the Key--Value cache of transformer language models. The singular value spectrum of a rating matrix is shown to be a diminishing marginal utility schedule for latent factors, the eigenvalue spectrum of the projected covariance operator to be the marginal utility schedule of a model's learned representation, and cache eviction and low-rank cache compression to be instances of constrained utility maximization under a memory budget. The three collapse into a single allocation rule: retain the top dimensions whose eigenvalue exceeds the shadow price of the binding constraint. The framework is applied to the automated extraction of structured information from geo-mining documents, where it motivates a multi-pass inference protocol, a layer-wise TIES model merging procedure, and a selection policy combining extraction quality, localization drift and energy, scalarized with a Conditional Value-at-Risk term on drift. Two empirical contributions are reported. An 11.2-million-parameter hierarchical classifier, trained in about five minutes on a single GPU, reaches 90.0 per cent level-1 accuracy on a held-out test set from a 973-document uranium-exploration corpus, against 92.0 per cent for a proprietary model on a fifty-document human audit of the same corpus, at a latency of 2.62 ms per card against approximately 2,000 ms for the API and at negligible cost. A diagnostic of uniform-density TIES merging exposes a reproducible degenerate mode in which the merged model returns token-identical outputs across five geographically distinct districts while declaring high confidence; re-executing the merge under layer-wise calibrated densities removes that signature on the diagnostic sample. The full-scale extraction benchmark, including LoRA fine-tuning, is reported as projected rather than measured and remains an empirical extension of this work.

Caroline Gans Combe

INSEEC · INSEEC Business School / Omnes Education, Paris.

Cost-Aware Inference KV-Cache Compression Model Merging

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