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

May 5, 2026cs.AI

QKVShare: Quantized KV-Cache Handoff for Multi-Agent On-Device LLMs

Multi-agent LLM systems on edge devices need to hand off latent context efficiently, but the practical choices today are expensive re-prefill or full-precision KV transfer. We study QKVShare, a framework for quantized KV-cache handoff between agents that combines token-level mixed-precision allocation, a self-contained CacheCard representation, and a HuggingFace-compatible cache injection path. Our current results support a narrower but clearer story than the original draft: on 150 GSM8K problems with Llama-3.1-8B-Instruct, adaptive quantization remains competitive under repeated handoff and shows its clearest gains against uniform quantization in deeper-hop, higher budget settings; for handoff latency, the QKVShare path reduces TTFT relative to full re prefill at every tested context, from 130.7 ms vs. 150.2 ms at nominal 1K context to 397.1 ms vs. 1029.7 ms at nominal 8K context;. Stage timing shows that post-injection generation, not card creation, dominates the current QKVShare latency path. These results position quantized KV handoff as a promising on-device systems direction while also highlighting the need for stronger controller ablations and apples-to-apples runtime comparisons.

Pratik Honavar, Tejpratap GVSL

Mixed-Precision Quantization Multi-Agent LLM Systems KV Caching KV-Cache Management KV-Cache Quantization On-Device Inference

May 5, 2026cs.LG

HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization

KV-cache quantizers usually optimize storage-space reconstruction, even though attention reads keys through logits and values through attention-weighted readout. We argue that persistent cache error should be measured in model-visible coordinates. For keys, the visible object is score error modulo constant shifts; this yields HeadQ, a key-side method that stores a low-rank residual side code in a calibration-learned query basis and applies it as an additive logit correction. For values, fixed-attention readout gives an

A^2

-weighted token-distortion surrogate. Across six models, Fisher/score-space error predicts attention KL far better than raw key MSE; same-budget counterexamples, null-space interventions, query-PCA controls, and wrong-sign HeadQ falsify storage-MSE alternatives. Matched Pythia checkpoints localize the main anomaly to a small-model low-entropy route-flip boundary. In K-only WikiText-103 decode experiments with dense values, HeadQ removes roughly

84

--

94\%

of the excess perplexity on the strongest 2-bit rows; in an auxiliary full-KV 2-bit composition, HeadQ plus an

A^2

value policy improves all six models.

Jorge L. Ruiz Williams

Independent Researcher

Self-Attention KV Caching Attention Quantization KV-Cache Compression KV-Cache Quantization Post-Training Quantization+1

May 3, 2026cs.LG

Stochastic Sparse Attention for Memory-Bound Inference

Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all

n_k

key and value vectors from KV cache. We present Stochastic Additive No-mulT Attention (SANTA), a method that sparsifies value-cache access by sampling

S \ll n_k

indices from the post-softmax distribution and aggregates only those value rows. This yields an unbiased estimator of the post-softmax value aggregation while replacing value-stage multiply-accumulates with gather-and-add. We introduce stratified and systematic sampling to design variance-reduced, GPU-friendly variants. Evaluated on Llama-3.1-8B-Instruct at 32k-token contexts, S

^2

ANTA matches baseline accuracy while achieving up to

1.5\times

decode-step attention-kernel speedup over FlashInfer and FlashDecoding on an NVIDIA RTX 6000 Ada. In batched long-context generation, these kernel gains translate to up to

1.25\times

end-to-end decode-latency speedup. Finally, we propose Bernoulli

qK^\mathsf{T}

sampling as a complementary technique to sparsify the score stage, reducing key-feature access through stochastic ternary queries. Both methods are complementary to upstream quantization, low-rank projection, KV-cache compression, and KV-cache selection methods. Together, they point toward sparse, multiplier-free, and energy-efficient inference. We open-source our kernels at: https://github.com/OPUSLab/SANTA.git

Kyle Lee, Corentin Delacour, Kevin Callahan-Coray +5

Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA · Department of Electrical and Computer Engineering, University of Michigan, Ann Arbor, MI, USA · Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA

GPU Acceleration Self-Attention KV Caching Long-Context Language Model Inference KV-Cache Management LLM Inference Acceleration+1

May 3, 2026cs.CV

Decouple and Cache: KV Cache Construction for Streaming Video Understanding

Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded streams. Secondly, due to the high cost of collecting and training on unbounded streams, models must learn from short sequences while generalizing to long streams. Existing streaming VideoVLLMs fail to scale to unbounded video streams or focus on cache reuse strategies, leaving the impact of cache construction underexplored. In this paper, we propose Decoupled Streaming Cache(DSCache), a training-free cache construction mechanism that adapts pretrained offline models to streaming settings. DSCache maintains a cumulative past KV cache while constructing a separate instant cache on-demand, decoupled from past caches to preserve the informativeness of recent inputs. To enable position extrapolation beyond the training length, DSCache further incorporates a position-agnostic encoding strategy, ensuring KV caches to support unseen positions and preventing position overflow. Experiments on Streaming Video QA benchmarks demonstrate DSCache's state-of-the-art performance, with an average 2.5% accuracy gains over prior methods.

Zhanzhong Pang, Dibyadip Chatterjee, Fadime Sener +1

National University of Singapore.

Streaming Video Understanding KV Caching Efficient VLM Inference KV-Cache Management

May 3, 2026cs.CL

Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving

Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks. This paper presents a workload-aware benchmark of representative KV-cache optimization mechanisms spanning quantization, pruning, and merging, including KIVI, TurboQuant, SnapKV, and CaM, evaluated on LongBench-style multi-document QA, single-document QA, few-shot learning, and summarization workloads using Llama-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3. The benchmark measures task quality, mean output throughput, mean time-to-first-token, and realized compression ratio across context-length buckets. The results show that the compression ratio alone is a poor predictor of end-to-end performance. KIVI4 provides the most stable quality across models, SnapKV delivers the strongest long-context throughput, and CaM yields large gains on selected QA workloads but exhibits substantial workload sensitivity in both quality and realized compression ratio. These findings motivate workload-aware selection of KV-cache mechanisms rather than one-size-fits-all compression and provide deployment guidance for long-context serving systems.

Nikita Agrawal, Ruben Mayer

University of Bayreuth

LLM Serving KV Caching Long-Context Language Model Inference KV-Cache Management KV-Cache Compression KV-Cache Quantization+1

May 3, 2026cs.DC

SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving

Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers generate a KV cache that must be transferred to decode workers before generation can begin. With these workers residing on different physical systems, this transfer becomes a significant bottleneck to serving LLMs at scale, especially for long-input and agentic workloads. Existing lossless codecs are unsuitable here as they primarily target offline weight compression, run on CPUs, or use variable-length coding whose compression cannot keep up with KV production during prefill. We introduce SplitZip, a GPU-friendly lossless compressor for KV cache transfer that preserves KV tensors bitwise and integrates into existing serving frameworks without modifying model execution. SplitZip exploits redundancy in floating-point exponents of KV activations, encoding frequent exponent values with fixed-length codes and routing rare exponents through a sparse escape stream of (position, value). A calibrated top-16 exponent codebook eliminates online histogramming, while the regular dense path and sparse escape correction make both encoding and decoding efficient on GPUs. On real BF16 activation tensors, SplitZip achieves

613.3

GB/s compression throughput and

2181.8

GB/s decompression throughput, outperforming prior lossless compressors on the critical codec path. End-to-end transfer experiments show up to

1.32\times

speedup for BF16 KV cache transfer,

1.30\times

speedup for TTFT, and

1.23\times

increase in Request Throughput. The same approach extends to FP8 KV caches, providing up to

1.14\times

compression over native E5M2. Code is available at https://github.com/Intelligent-Microsystems-Lab/SplitZip

Yipin Guo, Siddharth Joshi

University of Notre Dame IN, USA

LLM Serving KV Caching Disaggregated LLM Serving LLM Inference Acceleration KV-Cache Compression

May 1, 2026cs.CV

Make Your LVLM KV Cache More Lightweight

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial GPU memory overhead due to the large number of vision tokens processed during the prefill stage. To tackle this problem, we propose LightKV, a novel approach that reduces KV cache size by exploiting the redundancy among vision-token embeddings. Guided by text prompts, LightKV employs cross-modality message passing to aggregate informative messages across vision tokens and progressively compress them during prefill. This prompt-aware guidance distinguishes our method from prior vision-only compression strategies. We evaluate LightKV on eight open-source LVLMs across eight public benchmark datasets, e.g., MME and SeedBench. Experimental results demonstrate that with only 55% of the original vision tokens, LightKV (a) halves the vision-token KV cache size, (b) reduces computation by up to 40%, and (c) preserves general-purpose performance while significantly outperforming existing baselines.

Xihao Chen, Yangyang Guo, Roger Zimmermann

Integrative Sciences and Engineering Programme, National University of Singapore · School of Computing, National University of Singapore

KV Caching Efficient VLM Inference Large Vision-Language Models KV-Cache Compression Visual Token Compression

May 1, 2026cs.CL

KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression

Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput. To address these issues, KV cache compression has emerged as a promising technique for reducing memory overhead by selectively removing unimportant KV pairs while preserving useful ones for subsequent decoding. Nevertheless, we identify two key limitations in existing KV cache compression methods: 1) their threshold-triggered compression policy may provide limited throughput improvement or even reduce throughput, and may fully eliminate KV pairs from certain blocks of the sequence, potentially worsening information loss. 2) they typically retain either isolated KV pairs or fixed-size chunks with rigid boundaries, failing to preserve important flexible-sized chunks at arbitrary token positions. To overcome these limitations, we propose Kara, a sliding-window KV cache compression method that performs decoding-time compression by operating only on the recently generated context. Kara leverages bidirectional attention to score and select informative KV pairs in the window. To enable flexible preservation of important semantic information, we design a Token2Chunk module to expand a subset of selected KV pairs into chunks. Furthermore, we adapt Kara to PagedAttention and develop KvLLM, an inference framework built upon vLLM, which reduces KV cache memory usage and effectively improves output throughput. Extensive experiments demonstrate consistent performance improvements of proposed Kara and KvLLM.

Shen Han, Yuyang Wu, Junpu Yu +1

Carnegie Mellon University

KV Caching Memory-Efficient Inference LLM Inference Acceleration KV-Cache Compression

Apr 29, 2026cs.LG

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent subset of the KV state per decoding step and extending the KV storage to CPU memory. In practice, however, these algorithmic savings rarely translate into end-to-end system-level gains because sparse methods typically operate at different granularities and thus rely on ad hoc, per-algorithm implementations. At the same time, hierarchical KV storage introduces a new systems bottleneck: retrieving fine-grained, irregular KV subsets across the GPU-CPU boundary can easily erase the benefits of sparsity. We present SPIN, a sparse-attention-aware inference framework that co-designs the execution pipeline with hierarchical KV storage through three techniques: (1) a unified partition abstraction that maps different sparsity granularities onto a shared page-based KV substrate; (2) a locality-aware KV cache manager that dynamically sizes per-request HBM budgets and uses a GPU-friendly bucketed LRU policy to cut PCIe round-trips; and (3) a two-level hierarchical metadata layout sized to the active working set rather than the worst-case address space. Built on vLLM with three representative sparse attention algorithms, SPIN delivers 1.66-5.66x higher end-to-end throughput and 7-9x lower TTFT than vLLM, and reduces TPOT by up to 58% over the original sparse-attention implementations.

Zihan Zhao, Baotong Lu, Shengjie Lin +8

University of Virginia · Microsoft Research · Georgia Institute of Technology +1

LLM Serving KV-Cache Offloading KV Caching Long-Context Language Model Inference KV-Cache Management Sparse Attention

Apr 28, 2026cs.LG

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective

Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies predominantly rely on empirical heuristics, lacking a rigorous theoretical foundation. This work rethinks KV cache eviction through the lens of the Information Bottleneck principle. Under a linear-Gaussian surrogate of attention, we derive a closed-form mutual information objective that characterizes the effective information capacity of a retained KV cache subset. This formulation reveals that a wide range of existing eviction strategies can be interpreted as different approximations of the same capacity-maximization principle. Guided by this insight, we introduce CapKV, a capacity-aware eviction method that directly targets information preservation via a log-determinant approximation using statistical leverage scores. This approach replaces heuristic selection with a theoretically grounded mechanism that preserves the maximum predictive signal. Extensive experiments across multiple models and long-context benchmarks show that CapKV consistently outperforms prior methods, achieving a better trade-off between memory efficiency and generational fidelity.

Jiaming Yang, Chenwei Tang, Liangli Zhen +1

College of Computer Science, Sichuan University, Chengdu, China · Institute of High Performance Computing, A*STAR, Singapore

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

Apr 27, 2026cs.LG

Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant

We analyse three KV cache quantization schemes under a fair bit budget: \textbf{KV} (scalar MSE baseline), \textbf{KQV} (WHT + MSE on

K

; WHT + MSE + QJL on

V

), and \textbf{QKQV} (WHT + MSE + QJL on both). Starting from the Beta distribution on the hypersphere, we trace how QJL on

K

inflates inner product variance by

π/2

, which softmax amplifies nonlinearly via Jensen's inequality, and we present statistical inference and information metrics to highlight practical differences. Three empirical findings emerge. (1)~At

n=4

(the practically dominant budget), KQV wins on every measure -- KL divergence, geometric

K

error, and 6D distance -- across all distributions and ranks tested. (2)~The K--V asymmetry is unconditional: QKQV is consistently worse than KQV in KL divergence at every budget and distribution. (3)~A budget-dependent crossover exists: QKQV achieves better geometric

K

reconstruction at

n \in \{2,3,5\}

, KQV at

n \in \{4,6\}

, invariant to rank and tail weight -- an open rate-distortion problem.

\mathrm{KL}(p_{\mathrm{ref}} \| p_{\mathrm{quant}})

, K-only by construction, bridges K direction error to routing corruption and output collapse. We present a sufficient condition when the Jensen mechanism amplifies superlinearly through the softmax. At

n \in \{2,3,5\}

, QKQV wins geometrically because this assumption does not bind. At

n=4

, elevated K error and KL divergence for QKQV strongly suggest the Jensen mechanism is the operative cause of the crossover, providing a new perspective and explanation.

Paolo D'Alberto

AMD

KV Caching Rate-Distortion Optimization KV-Cache Compression KV-Cache Quantization

Apr 27, 2026cs.LG

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference

We present PolyKV, a system in which multiple concurrent inference agents share a single, asymmetrically compressed KV cache pool. Rather than allocating a separate KV cache per agent -- the standard paradigm -- PolyKV writes a compressed cache once and injects it into N independent agent contexts via HuggingFace DynamicCache objects. Compression is asymmetric: Keys are quantized at int8 (q8_0) to preserve softmax stability, while Values are compressed using TurboQuant MSE -- a Fast Walsh-Hadamard Transform (FWHT) rotation followed by 3-bit Lloyd-Max quantization with centroids tuned to N(0,1). We evaluate across two model scales (SmolLM2-1.7B-Instruct and Llama-3-8B-Instruct), three context lengths (600-7,194 tokens), and up to 15 concurrent agents. PolyKV achieves a stable 2.91x compression ratio across all configurations. On Llama-3-8B with 15 agents sharing a 4K-token context, PolyKV reduces KV cache memory from 19.8 GB to 0.45 GB -- a 97.7% reduction -- while maintaining only +0.57% perplexity degradation and a mean BERTScore F1 of 0.928. PPL delta does not grow with agent count and improves as context length increases, inverting to -0.26% at 1,851 coherent tokens. To our knowledge, no prior work combines a single shared, lossy-compressed KV pool with multi-reader concurrent agent access.

Ishan Patel, Ishan Joshi

Independent Researcher

LLM Inference Efficiency Multi-Agent LLM Systems KV Caching KV-Cache Reuse KV-Cache Compression KV-Cache Quantization

Apr 27, 2026cs.CL

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference

Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. However, efficient autoregressive inference relies on the key-value (KV) cache, whose memory footprint grows linearly with sequence length, leading to a major memory bottleneck. To mitigate this overhead, KV cache pruning methods discard cached tokens with low attention scores during inference. Most existing methods apply a uniform pruning ratio across layers, implicitly assuming that all layers contribute equally to overall model performance. We show that this assumption is suboptimal, as layers differ significantly in their sensitivity to pruning. We propose DepthKV, a layer-dependent pruning framework that allocates a fixed global KV budget across layers based on their sensitivity, rather than using a uniform allocation. Across multiple models and tasks, DepthKV consistently outperforms uniform pruning at the same global pruning ratio, demonstrating more effective utilization of the KV cache budget through layer-dependent allocation.

Zahra Dehghanighobadi, Asja Fischer

1Ruhr University Bochum · 2UAR Research Center for Trustworthy Data Science and Security

LLM Pruning KV Caching Long-Context Language Model Inference KV-Cache Management Memory-Efficient Inference KV-Cache Pruning

Apr 27, 2026cs.CL

Kwai Summary Attention Technical Report

Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the standard softmax attention exhibits quadratic time complexity with respect to sequence length. As the sequence length increases, this incurs substantial overhead in long-context settings, leading the training and inference costs of extremely long sequences deteriorate rapidly. Existing solutions mitigate this issue through two technique routings: i) Reducing the KV cache per layer, such as from the head-level compression GQA, and the embedding dimension-level compression MLA, but the KV cache remains linearly dependent on the sequence length at a 1:1 ratio. ii) Interleaving with KV Cache friendly architecture, such as local attention SWA, linear kernel GDN, but often involve trade-offs among KV Cache and long-context modeling effectiveness. Besides the two technique routings, we argue that there exists an intermediate path not well explored: {Maintaining a linear relationship between the KV cache and sequence length, but performing semantic-level compression through a specific ratio

k

}. This

O(n/k)

path does not pursue a ``minimum KV cache'', but rather trades acceptable memory costs for complete, referential, and interpretable retention of long distant dependency. Motivated by this, we propose Kwai Summary Attention (KSA), a novel attention mechanism that reduces sequence modeling cost by compressing historical contexts into learnable summary tokens.

Chenglong Chu, Guorui Zhou, Guowang Zhang +35

Kuaishou

Self-Attention KV Caching Long-Context Language Model Inference Long-Context Language Modeling Transformer Attention Attention Mechanisms+1

Apr 24, 2026cs.LG

MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches

Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long user histories. While cross-request Key-Value (KV) cache reuse presents a significant optimization opportunity, the massive scale of individual user states creates a storage explosion that far exceeds physical GPU limits. We propose MTServe, a hierarchical cache management system that virtualizes GPU memory by leveraging host RAM as a scalable backup store. To bridge the I/O gap between tiers, MTServe introduces a suite of system-level optimizations, including a hybrid storage layout, an asynchronous data transfer pipeline, and a locality-driven replacement policy. On both public and production datasets, MTServe delivers up to 3.1* speedup while maintaining near-perfect hit ratios (>98.5%).

Xin Wang, Chi Ma, Shaobin Chen +14

School of Computer Science, Wuhan University · Meituan · Nvidia

KV-Cache Offloading KV Caching Memory-Efficient Optimization KV-Cache Management KV-Cache Reuse Generative Recommendation

Apr 23, 2026cs.LG

Sub-Token Routing for KV Cache Compression

Transformer inference often requires a large KV cache, especially for long-context language modeling and multimodal generation. Existing compression methods usually reduce cache cost by selecting, evicting, quantizing, or compressing cached tokens, or by reducing the visual-token sequence before language-model inference. We introduce sub-token routing, a KV-compression method that adds a finer control axis inside retained tokens. It splits each retained value vector into groups and keeps only selected groups, while leaving query and key states unchanged. The method is designed to work after token-level reduction. First, a token-reduction method determines which tokens are retained. Then, sub-token routing compresses the value states inside those retained tokens. Experiments under matched KV budgets show that adding sub-token routing improves token-level reduction performance in both LLM and VLM settings, including Quest on LLaMA-2-7B and Qwen2.5-7B, and FastV/VisionZip across LLaVA and Qwen-VL models. The gains are larger at smaller KV budgets, suggesting that value-group routing is especially useful when further token removal becomes costly. Overall, token-level reduction and sub-token routing provide complementary ways to reduce KV cost.

Wei Jiang, Wei Wang

Futurewei Technologies San Jose, CA 95131, USA

LLM Inference Efficiency KV Caching Efficient VLM Inference KV-Cache Compression

Apr 22, 2026cs.LG

LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction

Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentally limited by heuristics: heuristic budgeting relies on statistical priors rather than task objectives, causing resource misallocation, while heuristic selection relies on coupled query-key interactions or static inductive biases (e.g., attention sinks). To address this limitation, we introduce LKV (Learned KV Eviction), which formulates KV compression as an end-to-end differentiable optimization problem. LKV integrates LKV-H to learn task-optimized global budgets, and LKV-T to derive intrinsic KV importance without materializing attention matrices. This design bypasses heuristic proxies, strictly aligning compression with task objectives. Extensive evaluations demonstrate that LKV achieves state-of-the-art performance on both LongBench and RULER benchmarks at high compression rates. In particular, on LongBench, LKV achieves near-lossless performance with only 15% KV cache retention. Crucially, our analysis identifies learned budgeting as the dominant driver of fidelity, demonstrating that data-driven allocation is essential to overcome the limitations of hand-crafted heuristics.

Enshuai Zhou, Yifan Hao, Chao Wang +7

University of Science and Technology of China, Hefei, China · State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China · University of Chinese Academy of Sciences, Beijing, China

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

Apr 22, 2026cs.LG

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory

Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving. Quantizing the KV cache to fewer bits reduces this cost, yet all current quantizers assign the same bit-width to every attention head, ignoring the large variation in head importance. A natural idea is to allocate more bits to important heads and fewer to the rest. We show, however, that such mixed-precision allocation has a hidden pitfall: each quantizer follows a different distortion curve D(b)=alpha*beta^{-b}, and the decay rate beta varies from 3.6 to 5.3 across quantizer designs. Applying one quantizer's distortion model to another inverts the allocation order and makes performance worse than uniform quantization. We call this failure mode distortion model mismatch and propose RateQuant to resolve it. RateQuant fits a per-quantizer distortion model from a small calibration set, then solves the resulting bit-allocation problem in closed form via reverse waterfilling from rate-distortion theory. On Qwen3-8B at 2.5 average bits, calibrated RateQuant reduces KIVI's perplexity from 49.3 to 14.9 (70% reduction) and improves QuaRot by 6.6 PPL. The entire calibration takes 1.6 s on a single GPU and adds zero overhead at inference time.

Fei Zuo, Zikang Zhou, Hao Cong +2

1BA TechWorks (BMW Group) · 2National University of Singapore · 3Tsinghua University

LLM Inference Efficiency Mixed-Precision Quantization LLM Quantization KV Caching Memory-Efficient Optimization Rate-Distortion Optimization+1

Apr 21, 2026cs.LG

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving

KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent workloads. Although many KV-cache compression methods improve offline accuracy or compression ratio, they often violate practical serving constraints such as paged memory layouts, regular memory access, and fused attention execution, limiting their effectiveness in deployment. In this work, we identify the minimal set of 4-bit KV-cache quantization methods that remain viable under these constraints. Our central finding is that a simple design--token-wise INT4 quantization with block-diagonal Hadamard rotation--consistently achieves the best accuracy-efficiency trade-off. Across multiple models and benchmarks, this approach recovers nearly all of the accuracy lost by naive INT4, while more complex methods such as vector quantization and Hessian-aware quantization provide only marginal additional gains once serving compatibility is taken into account. To make this practical, we implement a fused rotation-quantization kernel that integrates directly into paged KV-cache layouts and introduces zero measurable end-to-end overhead, matching plain INT4 throughput across concurrency levels. Our results show that effective KV-cache compression is fundamentally a systems co-design problem: under real serving constraints, lightweight block-diagonal Hadamard rotation is a viable method that delivers near-lossless accuracy without sacrificing serving efficiency.

Jinda Jia, Jisen Li, Zhongzhu Zhou +8

Together AI

LLM Serving KV Caching Memory-Efficient Optimization 4-Bit Quantization Rotation-Based Quantization LLM Inference Acceleration+2

Apr 20, 2026cs.LG

How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers

The key-value (KV) cache is the dominant memory bottleneck during Transformer inference, yet little is known theoretically about how aggressively it can be compressed before multi-step reasoning degrades. We study this through

k

-hop pointer chasing on

n

tokens under a shared KV cache of size

s

, attention dimension

m

,

H

heads,

p

-bit precision, and a locality-respecting cache controller (satisfied by all standard KV-compression methods). We give three results. (1) Product depth lower bound (conjectured). We conjecture that any such Transformer (

n \geq 4k

,

s \leq \sqrt{n}/4

) requires depth

L = Ω(\lceil k/s \rceil \cdot \lceil \log_2 n/(Hmp) \rceil)

, and isolate the sole remaining gap as a probabilistic step on the joint distribution of cache trace and pointer chain. Unconditionally, we prove a matching upper bound

L = O(\min(k, \lceil k/s \rceil \log s) \cdot \log n/(mp))

via windowed pointer doubling, and a max-bound

L = Ω(\max(\lceil k/s \rceil, \log n/(Hmp)))

. Closing the conjecture amounts to upgrading max to product. (2) Bandwidth barrier. The product bound binds only when

Hmp \lesssim \log n

. Any lower bound provable via per-window distinguishability counting -- including reachability, bandwidth, and combinations -- cannot exceed

\lceil k/s \rceil

once

Hmp \geq \log_2 n

. Breaking this requires lifting unconditional communication-complexity bounds for pointer chasing to Cache-Transformer depth. (3) Adaptive vs oblivious error scaling. Under random cache over

T = \lceil \log_2 k \rceil

doubling stages, oblivious caches give

\Pr[\mathcal{E}] \leq (s/(n-T))^T + 2T^3/n

(exponential in

T

), while adaptive locality-respecting caches achieve

\Pr[\mathcal{E}] = s/n

exactly, independent of

T

. The

Ω((n/s)^{T-1})

separation explains why heavy-hitter eviction empirically dominates random eviction for multi-hop reasoning.

Xiao Wang

Transformer Inference KV Caching KV-Cache Management KV-Cache Compression Communication Complexity

Apr 20, 2026cs.LG

MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression

KV cache memory is the dominant bottleneck for long-context LLM inference. Existing compression methods each act on a single axis of the four-dimensional KV tensor -- token eviction (sequence), quantization (precision), low-rank projection (head dimension), or cross-layer sharing -- but apply the same recipe to every layer. We show that this homogeneity leaves accuracy on the table: different layers respond very differently to each compression operation, and the optimal per-layer mix of eviction and quantization is far from uniform. We propose MoE-nD, a mixture-of-experts framework that routes each layer to its own (eviction-ratio, K-bits, V-bits) tuple under a global memory budget. An offline-calibrated greedy solver chooses the routing that minimizes predicted quality loss; at inference time, per-layer heterogeneous eviction and quantization are applied jointly through a single attention patch. On a 4-task subset of LongBench-v1 (16k inputs, n=50 per task, adapted reasoning-model protocol; see section Experiments), MoE-nD's hetero variant matches our uncompressed 1.9~~GB baseline at 14x compression (136~~MB) while every other compressed baseline we tested (1d, 2d_uniform, 2d) at comparable or smaller memory stays under 8/100. The gains hold on AIME reasoning benchmarks (+6 to +27 pts over the strongest per-layer-quantization baseline across eight configurations). Two null results -- MATH-500 and LongBench's TREC -- share a principled cause (short inputs, solver picks keep=1.0 on most layers), cleanly characterizing when per-layer eviction routing has headroom to help.

Libo Sun, Peixiong He, Po-Wei Harn +1

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

LLM Inference KV Caching Memory-Efficient Optimization KV-Cache Eviction KV-Cache Compression KV-Cache Quantization

Apr 19, 2026cs.AR

Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference

Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache sizing across all attention architectures--particularly multi-head latent attention (MLA), which is unsupported in general-purpose frameworks, resulting in up to 57x memory over-provisioning; (2) confinement of KV cache to a single memory tier (GPU HBM) despite the availability of a rich hierarchy spanning CPU DRAM, CXL-attached memory, NVMe via GPUDirect Storage, RDMA fabric, and parallel filesystems; and (3) reactive eviction policies that discard reusable state, forcing redundant recomputation. We present a unified system that addresses all three problems. Our architecture-variant-aware sizing engine computes exact memory requirements per attention type, enabling up to 7.4x higher batch sizes. A six-tier memory hierarchy extends effective KV cache capacity from 40 GB to over 38 TB per node while maintaining sub-millisecond time-to-first-token (TTFT) for hot entries. A Bayesian reuse predictor with Beta conjugate priors over 16 (block-type, transition-type) pairs achieves 70-84% cache hit rates, combined with EMA-scored head-granular eviction and RoPE-aware prefetching. Component-level validation on trace replay using ShareGPT, LMSYS-Chat-1M, and agentic workloads demonstrates 70-84% cache hit rates. Analytical projections combining validated component behavior with published hardware specifications indicate 1.4-2.1x projected TTFT reduction, 1.7-2.9x throughput improvement, and 47% cost reduction compared to state-of-the-art baselines.

Sanjeev Rao Ganjihal

Independent Researcher

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

Apr 16, 2026cs.CV

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression

Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing

O(1)

frameworks primarily rely on a ``pure eviction'' paradigm, which suffers from significant information destruction due to binary token deletion and evaluation noise from localized, single-layer scoring. To address these bottlenecks, we propose StreamCacheVGGT, a training-free framework that reimagines cache management through two synergistic modules: Cross-Layer Consistency-Enhanced Scoring (CLCES) and Hybrid Cache Compression (HCC). CLCES mitigates activation noise by tracking token importance trajectories across the Transformer hierarchy, employing order-statistical analysis to identify sustained geometric salience. Leveraging these robust scores, HCC transcends simple eviction by introducing a three-tier triage strategy that merges moderately important tokens into retained anchors via nearest-neighbor assignment on the key-vector manifold. This approach preserves essential geometric context that would otherwise be lost. Extensive evaluations on five benchmarks (7-Scenes, NRGBD, ETH3D, Bonn, and KITTI) demonstrate that StreamCacheVGGT sets a new state-of-the-art, delivering superior reconstruction accuracy and long-term stability while strictly adhering to constant-cost constraints.

Xuanyi Liu, Chunan Yu, Deyi Ji +6

KOKONI 3D, Moxin Technology · Nanjing University of Science and Technology · University of Science and Technology of China +4

3D ViTs Streaming 3D Reconstruction KV Caching 3D Reconstruction Efficient ViTs Visual Token Compression+1

Apr 16, 2026cs.AI

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration

While chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning tasks, the linear growth of the KV cache leads to substantial memory and inference overhead. Existing approaches such as context compression and multi-token prediction (MTP) improve efficiency from two complementary directions by compressing historical tokens and generating future tokens in parallel. However, effectively combining them remains challenging due to their different training paradigms and architectural assumptions. In this work, we propose MemoSight (Memory-Foresight-Based Reasoning), a unified framework that integrates context compression and MTP to improve inference efficiency while preserving CoT performance. MemoSight adopts a shared minimalist design based on special tokens and token-specific positional layouts for both compression and parallel prediction. Experiments on four reasoning benchmarks show that, compared to the vanilla SFT baseline, MemoSight reduces KV cache usage by up to 66% and improves inference speed by 56%, while incurring less than a 3% drop in average reasoning accuracy, yielding a better efficiency-accuracy trade-off than existing CoT compression methods.

Xinyu Liu, Xin Liu, Bo Jin +8

School of Computer Science and Engineering, Northeastern University, China · Meituan Inc. · NiuTrans Research, Shenyang, China

Multi-Token Prediction KV Caching CoT Reasoning Memory-Efficient Optimization Memory-Efficient Inference LLM Inference Acceleration

Apr 14, 2026cs.LG

When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration

Communication in Large Language Model (LLM)-based multi-agent systems is moving beyond discrete tokens to preserve richer context. Recent work such as LatentMAS enables agents to exchange latent messages through full key-value (KV) caches. However, full KV relay incurs high memory and communication cost. We adapt KV-cache eviction methods to this setting and introduce \textbf{Orthogonal BackFill (OBF)} to mitigate information loss from hard eviction. OBF injects a low-rank orthogonal residual from discarded KV states into the retained KV states. We evaluate OBF against full KV relay on nine benchmarks spanning mathematical reasoning, expert and commonsense QA, and coding. With only 9.9%-20.2% of the prompt KV states retained, H-OBF delivers between

97%

and

120%

of full KV relay's per-benchmark accuracy across the nine benchmarks. This suggests that more information does not necessarily lead to better communication; preserving the most useful information matters more. Our codebase is included in the supplementary material. Our codebase is publicly available on https://github.com/markli404/When-Less-Latent-Leads-to-Better-Relay.

Yiping Li, Zhiyu An, Wan Du

Department of Computer Science and Engineering University of California, Merced Merced, CA 95343

LLM Compression KV Caching KV-Cache Compression Multi-Agent Communication Multi-Agent LLMs

Apr 13, 2026cs.LG

Attention-Weighted Value Projection for KV-Cache Compression

Rank reduction discards dimensions; quantization keeps them at lower precision. Comparing the two requires a choice of what compression should preserve. For attention values, we study reconstruction of the attention output rather than reconstruction of the values alone. With fixed attention weights, the optimal orthogonal rank-

r

projection uses the leading eigenvectors of

V^\topα^\topαV

, and its error is exactly the discarded eigenvalue sum. We extend this objective to calibration datasets and grouped query attention, and describe rank allocation under an additive local error budget. We also examine the limits of using local error to predict downstream loss. Historical weight-perturbation experiments favor coefficient rounding over the value projections tested, but do not establish a comparison at equal cache storage. The resulting distinction is practical: the projection objective has an exact solution, while a comparison with cache quantization requires separate activation-level experiments.

Samuel Salfati

fraQtl AI Research

Grouped-Query Attention KV Caching Efficient Attention Low-Rank Compression Low-Rank Approximation KV-Cache Compression

Apr 9, 2026cs.LG

KV Cache Offloading for Context-Intensive Tasks

With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising approach to reduce memory footprint and inference latency while preserving accuracy. Prior evaluations have largely focused on tasks that do not require extracting large amounts of information from the context. In this work, we study KV-cache offloading on context-intensive tasks: problems where the solution requires looking up a lot of information from the input prompt. We create and release the Text2JSON benchmark, a highly context-intensive task that requires extracting structured knowledge from raw text. We evaluate modern KV offloading on Text2JSON and other context-intensive tasks and find significant performance degradation on both Llama 3 and Qwen 3 models. Our analysis identifies two key reasons for poor accuracy: low-rank projection of keys and unreliable landmarks, and proposes a simpler alternative strategy that significantly improves accuracy across multiple LLM families and benchmarks. These findings highlight the need for a comprehensive and rigorous evaluation of long-context compression techniques.

Andrey Bocharnikov, Ivan Ermakov, Denis Kuznedelev +2

HSE, Yandex · Yandex · Yandex, NSU

KV-Cache Offloading KV Caching KV-Cache Management KV-Cache Compression

Mar 5, 2026cs.LG

InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context

Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts. A common strategy is to precompute key-value (KV) caches for individual documents and selectively recompute a small subset of tokens to restore global causal dependencies, but existing methods rely on heuristics or representation discrepancies without modeling whether selected tokens can effectively influence generation. We cast selective KV recomputation as an information flow problem and show that a simple attention-norm signal from the query reliably identifies tokens that are both semantically relevant and structurally positioned to propagate information, when computed under an inference-consistent RoPE geometry. We therefore reconstruct global positional assignments for retrieved chunks and introduce an information-flow-guided chunk reordering strategy. Experiments on Large Language Model and Vision-Language Model benchmarks demonstrate consistent gains over prior methods under comparable latency.

Xin Teng, Canyu Zhang, Shaoyi Zheng +3

New York University · New York University Shanghai · Duke University +1

Retrieval-Augmented Generation KV Caching Long-Context QA KV-Cache Management LLM Inference Acceleration

Feb 10, 2026cs.CL

Learning to Evict from Key-Value Cache

The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost but rely on heuristics, such as recency or past attention scores, which serve only as indirect proxies for a token's future utility and introduce computational overhead. We reframe KV cache eviction as a reinforcement learning (RL) problem: learning to rank tokens by their predicted usefulness for future decoding. To this end, we introduce KV Policy (KVP), a framework of lightweight per-head RL agents trained on pre-computed generation traces using only key and value vectors. Each agent learns a specialized eviction policy guided by a holistic reward, derived from future utility, that evaluates the quality of the ranking across all cache budgets, requiring no modifications to the underlying LLM or additional inference. Evaluated across two model families on the long-context benchmark RULER (up to 128K tokens) and the multi-turn dialogue benchmark OASST2-4k, KVP significantly outperforms strong baselines. Zero-shot tests on standard downstream tasks (BoolQ, LongBench passage retrieval, GovReport) further show that KVP generalizes beyond its training distribution and to considerably longer sequence lengths. These results demonstrate that learning to predict future token utility is a powerful and scalable paradigm for adaptive KV cache management.

Luca Moschella, Laura Manduchi, Ozan Sener

Apple

KV Caching Long-Context Language Model Inference KV-Cache Eviction KV-Cache Management

Feb 9, 2026cs.LG

Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference

A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-oracle top-k KV selection can preserve the quality of dense attention while sharply reducing computation and bandwidth, existing sparse methods generally rely on posterior heuristics, i.e., selectors conditioned on observed attention or proxy scores. Such conditioning introduces posterior bias: it tends to distort true token importance and miss salient tokens, thereby impairing long-range reasoning. To tackle this problem, we propose Pre-hoc Sparsity (PrHS), which selects KV entries before attention scoring and provides explicit accuracy control. Let the attention mass of discarded entries be delta (the dropped mass). Through a marginal-to-mutual-information analysis, we derive an upper bound on the mutual-information loss that depends only on the dropped mass. This relation explains failure modes of posterior heuristics and enables verifiable guarantees by controlling the dropped mass in advance. Within PrHS, we instantiate three orthogonal pre-hoc selectors along the axes of time, depth, and layer. Extensive experiments on LLaMA and Mistral families validate PrHS. Across GSM8K and CoQA, PrHS reduces retrieval overhead by over 90%, achieving 3x higher retrieval sparsity than HShare at matched or better accuracy. It incurs under 1% average degradation on LongBench, lowers attention FLOPs by about 15% versus prior sparse baselines, and yields a 9.9x speedup in attention-operator latency and 2.8x higher throughput on NVIDIA A100-80GB GPUs than the dense baseline.

Yifei Gao, Lei Wang, Rong-Cheng Tu +3

University College London, London, UK · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (CAS), Shenzhen 518055, China · The Chinese University of Hong Kong +1

Self-Attention KV Caching Long-Context Language Model Inference KV-Cache Management LLM Inference Acceleration Sparse Attention+1