Key-Value

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

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

Decoding-time KV cache compression research focuses heavily on designing better token scoring functions, while the temporal rule that aggregates scores across decode steps is often treated as an implementation detail. Under aggressive KV compression, we find that exponential-moving-average (EMA) aggregation makes approximately order-preserving scorer modifications largely indistinguishable at the eviction-set level. Value-norm and entropy variants remain highly correlated with attention and produce nearly unchanged retention sets, whereas KeyDiff, key norm, recency, and a learned scorer alter the ranking and degrade substantially. We associate this stability with the evaluated aggregation, which couples layer weighting and temporal retention. Building on this observation, we introduce InertiaKV, an EMA-based decoding-time eviction method, and InertiaKV-Lazy, its periodic-refresh variant, which yields 1.34-1.46x decode throughput relative to full refresh InertiaKV. We also study Score-Free decoding as a separate empirical operating point: it scores the full context once at the first decode step, freezes that ranking, and incurs an average quality change of +0.03 while removing all subsequent scoring. Across six open-weight backbones and the LongBench, LongBench-v2, and RULER benchmarks, the results identify temporal aggregation and ranking preservation as distinct, consequential design factors; they do not imply that scoring quality is irrelevant in general.

Large language models (LLMs) face severe memory bottlenecks in long-context inference due to the linearly growing size of key-value (KV) caches. Existing KV cache compression techniques typically rely on simple heuristics, overlooking the distinct functional roles of different attention heads. We present SGD-KV (Summarization-Guided KV Cache Compression), a head-aware framework that leverages a novel chunk-summarization diagnostic task to systematically identify and prioritize attention heads specialized in hierarchical information aggregation. Experiments on Qwen2.5-7B-1M and Qwen3-32B across diverse long-context benchmarks demonstrate that SGD-KV achieves state-of-the-art performance with contexts up to 1M tokens, while reducing KV cache memory usage by up to 75%. Our findings show that strategically allocating the KV cache budget based on the summarization score distribution of attention heads yields a superior efficiency-accuracy trade-off for long-context inference.

Spoken dialogue state tracking recovers slot-value pairs from speech, where ASR errors concentrate in entity values and persist across turns, making it both a generation and an editing problem. A strong per-turn text editor corrects much of this but, operating on the transcript alone, leaves three recoverable errors: a value predicted inconsistently across turns, an omitted slot, and a value the audio does not support. We present AVERT, which scores each candidate value by combining cross-turn agreement with a trained audio-conditioned verifier and resolves the three error types with three operators, vote, add, and swap, each restricted to the slots where its error is common. On SpokenWOZ, a base speech-LLM reaches 33.04 JGA, a text editor 38.34, and AVERT 40.13, without retraining either. This is in the range of a 1B end-to-end system that consumes the full spoken history (39.32), though AVERT uses two 1B decoders rather than one. The audio verifier contributes a statistically significant gain, and restricting each operator to a selected slot subset matters: removing it lets unrestricted voting overwrite correct categorical values and fall below the editor.

Modern large language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own prefill computation even when another model has already processed the same input. Existing KV-cache reuse mechanisms substantially reduce redundant computation within a single model, but generally assume that the producer and consumer of a cache are identical. We study \emph{cross-model KV sharing}, which translates the KV state produced by a source model into a representation that can be consumed by a different target model, including models that differ in scale, architecture, attention configuration, tokenizer, and model family. We evaluate the approach in both within-family and cross-family settings. For Qwen2.5-7B $\rightarrow$ Qwen2.5-1.5B, translated KV states improve LongBench2 accuracy from 27.59% to 34.48%, a gain of 6.89 percentage points over the native 1.5B baseline, while reducing handoff cost relative to native target prefill. For the cross-family Qwen2.5-1.5B $\rightarrow$ Gemma-2-2B setting, KV handoff reduces target-side prefill cost by up to 67.05% at 4K context length while maintaining decoding perplexity close to native-model baselines. In a more heterogeneous Llama3.1-70B $\rightarrow$ Qwen2.5-7B setting, cross-family handoff achieves 44.0% accuracy compared with 45.7% for native Qwen2.5-7B inference, while reducing measured latency from 899ms to 138ms. These results provide initial evidence that KV states can serve as transferable computational representations rather than strictly model-local caches, and motivate \emph{context mobility} as a systems abstraction for reducing redundant prefill across heterogeneous LLM and multi-agent inference workflows.

The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests. In multi-tenant deployments this cache is shared across tenants, creating a timing side channel: an adversarial tenant can reconstruct another tenant's private prompt by probing cache-hit latency. Three published attacks exploit it -- PROMPTPEEK, EarlyBird and InputSnatch -- reaching up to 100% attack success rate against unprotected vLLM and SGLang, with rates varying by cache architecture and prompt structure. We present KVGov, a governance layer addressing all three attack families' prefix-cache paths under one mechanism. A per-principal salt sigma_p = HMAC_K(secret, principal_id) seeds the block-hash chain, making cache keys cryptographically disjoint across principals. An ablation (N=1000 trials, seed 2026, deterministic judges) isolates this salt as the necessary and sufficient component. KVGov adds ORIGAMI, a Stackelberg water-filling audit scheduler that reduces adversary expected utility by 12.6% at realistic tenant heterogeneity (Gini 0.63), and an evolutionary stability analysis giving a 31.6% adversary-prevalence tipping point below which global caching remains stable. On real hardware (Qwen2.5-7B-Instruct, vLLM 0.26.0, NVIDIA A100) we measure a gate-verified cold/cached TTFT ratio of 0.22, confirming the channel is exploitable at production scale; the defense itself is evaluated in simulation calibrated to those measurements. We replicate the channel on an independent stack (llama.cpp on Apple Metal, ratio 0.093). Finally, isolation and cache efficiency need not conflict: identifying information resides only where prompts diverge, so injecting the salt at that boundary rather than the chain root retains an estimated 93% of the prefix-cache benefit with no cross-principal signal.

Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work reduces this footprint by evicting tokens that appear unimportant under attention-derived scores. However, such policies make an implicit irreversible decision: once a token is evicted, it cannot become useful again. We show that this assumption is brittle during decoding. Token and window importance drift as generated queries evolve, causing standard eviction policies to permanently discard states that later receive substantial attention under the full-cache model. To characterize this behaviour, we introduce Future Missed Mass and Global LIR, two diagnostics that measure future attention assigned to discarded states and the reactivation of historically inactive regions. We propose QEvict, a three-tier KV-cache management scheme that replaces binary retain-or-delete eviction with recoverable eviction. QEvict maintains high-confidence windows in full precision, stores intermediate windows in a quantized recoverable tier, and deletes only the lowest-confidence windows. During decoding, cumulative attention scores update window importance and when a quantized window becomes important again, it is dequantized and promoted to the full-precision. Under a fixed memory budget, this design preserves broader historical context while retaining exact full precision for the most important regions. Across long-context understanding, retrieval, and reasoning benchmarks, QEvict consistently improves over representative eviction and quantization baselines, reducing missed attention and improving information retention

Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during inference. We derive the expected attention score distortion caused by rank r key compression and show that it yields a covariance weighted low rank objective. Under a margin condition, controlling this distortion also improves top k recall. The optimal rank r solution has a closed form asymmetric factorization obtained from the SVD of the covariance weighted query key operator. This motivates SAKI, a training free KV cache index that directly preserves attention scores rather than key reconstruction quality. Across LLaMA 3.1 8B, Qwen 2.5 7B, Mistral 7B v0.1, and Llama 3.2 3B, SAKI outperforms key PCA at every tested rank. At rank 32, it removes 13 to 30 percent of PCA's remaining top 64 recall error, including improvements from 0.748 to 0.799 on LLaMA 3.1 8B and from 0.786 to 0.850 on Qwen 2.5 7B. It improves 68 to 89 percent of attention heads per model, with the largest gains in deeper layers. Predicted score MSE reductions closely match empirical measurements, with a Pearson correlation of 0.997, while ablation studies confirm that the gains arise from optimizing the attention score objective rather than covariance weighting alone. Analysis of the scoring operator further explains why weight only, invariant subspace, and key reconstruction methods can be suboptimal. SAKI uses random-matrix theory to separate genuine covariance signal from autocorrelated sampling noise, matching PCA with only 512 calibration tokens and adding value exactly where PCA sees no reliable signal.

The growth of context window lengths in Large Language Models (LLMs) significantly enhances their long-context capabilities but incurs prohibitive memory costs due to the Key-Value (KV) cache. Although low-rank compression of KV cache is a promising remedy, existing methods face a dilemma: offline approaches depend on external calibration data, whereas online approaches incur substantial compute for full-prompt decomposition and reconstruction. In this paper, we propose S$^4$R, which builds low-rank subspaces from selectively sampled tokens and computes attention over a sparsely reconstructed KV representation. S$^4$R uses prompt-aware initialization to build initial key/value bases from a representative prompt subset, trading off calibration-data dependence against prefilling cost. Because fully reconstructing the cache at every decoding step is prohibitively expensive and hurts throughput, we further adopt sparse reconstruction to retain only informative positions during decoding. Extensive experiments on LongBench and RULER with Llama and Qwen model families show that S$^4$R achieves up to 5$\times$ KV compression with near full-cache accuracy, combining the efficiency of fixed compression with the adaptability of prompt-dependent methods.

Genetic Programming Symbolic Regression (GPSR) generates mathematical expressions to model input-output relationships using an evolutionary process. A significant challenge in GPSR lies in the repeated evaluation of entire expressions or their sub-expression, which inflates computational runtime. To address this inefficiency, caching mechanisms have been employed to reduce redundant computations. However, prior studies predominantly employ a single caching strategy, offering limited insights into their comparative performance or memory-runtime trade-offs. In this paper, we present a comprehensive analysis of caching mechanisms for GPSR on synthetic and real-world datasets. We also include an empirical study of key-value usage frequencies under an infinitely large cache, offering insights into optimal cache sizing. Furthermore, we provide actionable guidelines for configuring caching strategies based on computational and memory constraints. Our findings indicate that complex caching mechanisms necessitate a minimum cache size to achieve computational time reductions. Conversely, lightweight caching strategies, such as Least Recently Used (LRU) and, notably, First-In-First-Out (FIFO), can significantly decrease computation time for fitness evaluations, which are a substantial component of the overall runtime.

Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years. Computational demands of large language models (LLMs) and their multi-modal variants during output generation can be partially alleviated by caching previous key and value calculations needed by subsequent scaled dot-product attention operations. However, this leads to another problem: the size of the resulting KV cache grows linearly with context length and quickly consumes all available GPU memory when either the prompt or the generated output are long. KV cache management periodically prunes entries from the cache thereby reducing its memory footprint while attempting to retain sufficient information for accurate generation. A by-product is faster inference speed. We propose a simple yet effective KV eviction scheme motivated by the insight that past tokens which can be well-predicted from more recent tokens are redundant and their associated keys and values can be removed from the cache. To score entries for eviction we run the model on the tokens in their original order, reusing the key and value representations already stored in the KV cache, and applying a counter-causal attention mask so that each position attends only to its future context. This is in-distribution, tied directly to the actual cache contents, and requires no additional training. To further reduce cost, we additionally propose a fast single-layer approximation that restricts the counter-causal pass to the last transformer layer, achieving a significant speedup per refresh cycle at marginal accuracy cost. We evaluate our strategy on various open-source LLMs and benchmark datasets showing competitive or improved performance over other state-of-the-art methods. Reference code is available at https://github.com/metacognitionai/counter_causal.

Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histories, that is shared across a user's many requests. Production memory systems (e.g., Mem0, MemGPT, and Zep) retrieve a relevant subset of this memory and inject it into the prompt, forcing the serving engine to repeatedly prefill the same content. As the retrieval budget grows, time-to-first-token (TTFT) increases even though the underlying memory is reused across requests. We present InferScale, a GPU-native LLM memory system that replaces repeated prompt prefilling with reusable KV state. InferScale precomputes each memory fact's KV representation, stores it alongside a semantic embedding on the GPU, retrieves relevant facts at serving time, and injects their KV directly into vLLM's paged cache. To support dynamically assembled memories under rotary position embeddings, we introduce Chunked RoPE, which stores keys before rotation and applies their serving-time positions during injection. However, encoding memory facts independently omits the cross-fact context available during joint prefilling. We mitigate this with Context-Window Encoding, which encodes each memory fact together with a small window of preceding conversation context while caching only the target fact's KV. InferScale is implemented through vLLM's KV-connector interface, requiring neither engine modifications nor model fine-tuning. Across three open-weight models on LoCoMo, InferScale keeps TTFT nearly constant as the retrieval budget increases: at k=50 it reduces TTFT by 72-79% (3.6-4.8x), achieves 60.3% accuracy versus 63.3% for Mem0 without serving-time recomputation, and delivers 3.7-4.5x the throughput under concurrent load. Reusable KV state thus decouples memory-conditioned serving latency from retrieved-context size while preserving application quality.

Multi-head latent attention (MLA) is increasingly important for long-context LLM inference because compact latent states replace the growing key-value (KV) cache and reduce decoding memory traffic. Yet most capable open checkpoints use multi-head or grouped-query attention (MHA/GQA), so conversion is needed to obtain MLA's cache efficiency without retraining from scratch. Speculative decoding offers complementary acceleration, but its speedup depends on agreement between draft proposals and target verification. We find that direct MHA/GQA-to-MLA conversion can sharply reduce this agreement: low-rank factorization and RoPE handling introduce attention-function errors that may be tolerable for standalone generation but substantially lower draft-token acceptance. We therefore formulate MLA draft construction as functional reconstruction rather than cache compression. Our end-to-end (E2E) method optimizes each converted MLA attention module to reproduce the post-output-projection response of its original MHA/GQA counterpart on calibration hidden states. This converter-agnostic post-conversion procedure preserves the converted cache and inference graph and requires neither verifier logits nor verifier supervision. We evaluate 192 model-converter-backend-method-task configurations spanning four Llama/Qwen draft-target pairs, TransMLA and MHA2MLA, HF and vLLM, and four 200-prompt tasks. With a 0.5-percentage-point reporting tolerance, Functional Reconstruction materially improves acceptance in 37 of 64 matched task cells, leaves 26 practically unchanged, and materially decreases one. Code and evaluation artifacts are available at https://github.com/swyhahaha/FunctionalMLA.

Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys are locally low-rank though globally high-rank: shared low-rank bases discard page-specific directions that a page's own compact basis retains. LOCKS gives every page its own spectral summary (resident, about a tenth the cache's size), reconstructs within-page logits, estimates each page's attention mass by log-sum-exp, and attends only the top pages; selection itself reads no candidate keys or values. Selecting on this summary alone stays within about a point of the full cache on long-document QA (LongBench-v1), tracks the read-every-key oracle on retrieval-dense RULER down to the smallest budgets, and shows its largest margins on long-form reasoning (AIME26, MATH-500), where baseline selectors collapse. At its shipped $2048$-token budget LOCKS matches FullKV aggregate quality at $100$K$+$ context while attending about $2\%$ of the tokens, and halves per-token decode latency ($2.0\times$ at $1$M tokens) against dense attention. LOCKS ships as a drop-in plugin for unmodified vLLM, with batched decode running in full CUDA graphs.

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

We present cayleyR, an R package for solving permutation puzzles by detecting cycle intersections in Cayley graphs. The core algorithm performs an iterative bidirectional search: from both the initial and target permutation states, random operation sequences generate cycles in the Cayley graph of the symmetric group Sn; their intersection yields a connecting path. When no direct intersection is found, a distance-guided bridge selection narrows the gap, and the process repeats. The package targets the TopSpin(n,k) puzzle, whose state space is a Cayley graph of Sn generated by a cyclic shift and a prefix reversal. We describe the mathematical framework, the algorithm, and its implementation, which combines a C++ hash-indexed state store with optional Vulkan GPU acceleration. The software is publicly available on CRAN.

Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems. In disaggregated inference, these workloads require transferring large Key-Value (KV) caches across the network, where decoding cannot begin until the transfer completes. Recent KV quantization techniques reduce data volume and alleviate this bottleneck, but existing schemes fail to achieve both low network-exposed latency and high inference accuracy. We challenge the assumption that the KV cache is an indivisible unit that must be fully received before use. We leverage the observation that different bits in the KV cache contribute unequally to attention computation and inference precision: the most significant bits capture the coarse structure of attention and the least significant bits refine precision. This property enables partial use of the KV cache during decoding. We present Lynx, a system that enables progressive, split-stream KV transfer by partitioning the KV cache into a high-priority Anchor stream carrying the most significant bits and a low-priority Residual stream carrying remaining precision. Decoding begins upon receipt of the Anchor stream and proceeds speculatively while the Residual stream is transferred concurrently, followed by verification that ensures equivalence to higher-precision decoding. Across multiple models and serving workloads, Lynx achieves Time-to-First-Token (TTFT) comparable to aggressive 4-bit KV quantization, while matching the accuracy of high-precision (BF16) inference, improving TTFT over standard 8-bit KV quantization by up to $1.43\times$ and improving accuracy over state-of-the-art by up to $5.1\%$.

Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budget (Top-k) retrieval or rely on proxy scores that are computationally expensive and biased. To address these limitations, we propose RaBitQCache, a novel sparse attention framework that utilizes randomized rotated binary quantization and high-throughput binary-INT4 arithmetic to efficiently estimate attention weights. Our proxy score serves as an unbiased estimator with a proven error bound, enabling adaptive Top-p retrieval that dynamically adjusts the token budget based on actual attention sparsity. We further implement a hardware-aware system with asynchronous pipelining and lazy updates to mask overhead. Evaluations demonstrate that RaBitQCache significantly accelerates inference and reduces memory I/O while preserving generation quality compared to state-of-the-art baselines. Code is available at https://github.com/Sakuraaa0/RaBitQCache.git.

Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages. Existing KV cache compression methods mainly rely on attention weights to estimate token importance. While attention effectively captures contextual relevance, it overlooks complementary information-theoretic signals related to predictive uncertainty and token informativeness. In this paper, we revisit token importance from a forward-looking perspective and introduce \textit{Forward Influence}, a metric that measures how compressed tokens affect future contexts. Our analysis reveals that tokens selected by attention scores mainly influence nearby contexts, whereas tokens associated with high predictive uncertainty exhibit substantially stronger influence on distant future contexts. Based on the observation, we propose \textbf{InfoKV}, an entropy-aware KV cache compression framework that incorporates information-theoretic signals. It combines token-level predictive uncertainty with layer-wise representation evolution and integrates the resulting entropy scores with attention scores during reasoning. Experiments on long-context reasoning benchmarks with Llama-3.1, Llama-3.2, and DeepSeek-R1 demonstrate that InfoKV consistently outperforms existing attention-based KV compression methods in both long prefilling and decoding scenarios.

Multimodal agents repeatedly re-examine the same video frames, UI screenshots, and rendered artifacts as their context window slides and reasoning iterates, yet every look-back re-encodes from scratch, because prefix caches serve reuse only at a fixed leading position. We show this recompute is avoidable, and identify exactly what naive KV reuse loses: the cross-chunk conditioning a chunk absorbs from its neighbours. This loss is asymmetric. The direct readout of a cached chunk is recovered exactly and for free by the standard state-merge. What remains is a diffuse, low-rank residue concentrated in deep layers, invisible to single-hop retrieval but precisely what multi-hop reasoning binds on. Blind reuse therefore leaves single-hop recall intact while halving multi-hop accuracy; this is the failure mode prior position-independent caches, designed for single-context or single-image reuse, do not address. We repair it with a small, training-free low-rank conditioning patch stored alongside each position-free chunk. Reuse reduces to one operator across MLA, GQA, and MHA: exact RoPE re-rotation to any target position, plus the patch that restores cross-chunk binding. This makes three window operations cheap: reorder (one patch serves every ordering of a cached set), sliding-window survival (surviving chunks relocate via rotation only, zero re-encode), and recall (an evicted chunk is rehydrated by its patch, never re-encoded). A rank-m patch recovers full task accuracy on cross-chunk-binding benchmarks, MM-NIAH across two attention families and two-page doc-QA, at a fraction of the KV footprint, and reconstructs re-prefill KV to within bf16 rounding in a production SGLang kernel across six backbones. The conditioning signal is strongest in redundant vision and video streams, making our solution most impactful where multimodal agents spend their recompute budget.

Key-value (KV) caching is a powerful technique for accelerating large language model inference and generation. Inference workloads are large and diverse, which makes them difficult to cache effectively. Existing cache management strategies adopt the least-recently-used policy for evicting cache blocks. However, LRU leads to multiple unrelated workloads flushing each other's caches. To address this, we integrate adaptive caching that dynamically allocates cache space between recently and frequently occurring KV blocks. Evaluations show that it improves the KV cache hit rate by up to 10.8% and reduces time to first token by up to 12.6% over naive vLLM on synthetic document question answering workloads, and 2.1% and 2.0% respectively on real-world conversation workloads. The method generalizes well to batch inference and demonstrates clear interpretability while effectively accommodating diverse workloads.

Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of execution state: the KV cache. We study the opposite regime: low-latency, small-batch, on-device physical-AI serving, where interactive LLM agents, speech systems, and robot policies repeatedly branch, reset, interrupt, and re-enter under tight responsiveness budgets. We introduce execution-state capsules, a graph-bound checkpoint and restore mechanism for the complete restorable state at a committed boundary. FlashRT is a white-box, backend-facing kernel runtime whose evaluated NVIDIA CUDA backend runs captured graph plans over contiguous static buffers with no block-table indirection. Because the live state is a closed set of named buffers, a capsule can snapshot, restore, fork, or roll back the whole execution boundary, including KV, recurrent state, convolution state, MTP state, and metadata. This moves reuse from token-addressed KV fragments to graph-bound execution-state boundaries. On an RTX 5090, capsule restore is byte-exact at the stored-state level and token-identical under greedy decode. A KV-only ablation diverges, showing that recurrent state is load-bearing. GPU-resident snapshot and restore are sub-millisecond, and TTFT speedup over cold prefill grows from 3.9x at 2k tokens to 27x at 16k tokens. On Jetson AGX Thor and DGX Spark, the same correctness and structural properties hold. Capsules are not a replacement for high-throughput KV-cache serving; they define a complementary latency-first serving point for explicit execution-state reuse.

Right now, across the world, AI agents are repeating the same absurd act: to read one document, they each recompute it from scratch. Every agent re-runs prefill, the most compute-intensive step a large model takes, over identical text, only to rebuild a key-value (KV) cache identical to the one the agent before it just built. The same answer, computed a million times. We make a proposal that is almost offensively simple: compute it once. Let a publisher precompute a document's KV cache, and let every other agent buy the right to load it and skip prefill. It works, and it is token-exact: loading a precomputed KV and continuing matches prefilling from scratch (24/24 greedy tokens, and at the logits level), with no accuracy cost. On Qwen3-4B, reuse is 9-50x cheaper in compute than prefill, and the gap widens with length (prefill's attention scales with L^2), so a single reuse already pays it back. Then the part that matters: where the KV lives. Shipping it fails, because KV is nearly incompressible, so per-load egress costs more than the prefill it saves. Hosting it provider-side, exactly as production prompt-caching works, removes egress entirely. The size of the prize is set by our measured compute saving: serving one hot 3774-token document to 80M agents costs ~$1.5M to re-prefill but only ~$0.03M of reuse compute (49.7x less). The 0.1x cache-read tariff APIs charge passes a 10x discount to users while sitting inside this measured envelope, so the 10x is a floor that the measured ~50x compute saving clears, and the gap to the physical ~50x is provider margin: millions of dollars per popular document. We frame the resulting agent-native prefill CDN and leave lossless KV compression and a cross-party payment layer as the open problems.

How far can we reduce the number of physical keys if we endow an ambiguous keyboard with modern language models? Fewer keys increase hardware design freedom in constrained settings such as assistive devices and mobile form factors. This paper systematically evaluates text entry systems using 2-5 physical keys combined with language-model-based disambiguation. On a 300-sentence English corpus (100 sentences each for Business / Conversational / Technical), we compare key counts (2-5), letter-to-key mappings (layout-based / frequency-based / intentionally worst-case), and decoders (Trie-only, GPT-2 beam search, GPT-4o selection). We find that 3 keys + GPT-4o achieves character error rate (CER) 9.46% and word error rate (WER) 12.20%, reducing CER by 59% relative to 2 keys (CER 23.3%). At 3 keys, the key-stream entropy is 1.54 bits/char; while increasing to 5 keys improves accuracy (CER 5.4%), the marginal gains diminish. Mapping choice has a small impact under standard designs (ΔCER < 0.5 pp), and even an intentionally worst mapping degrades CER by only +0.5 pp, whereas Technical sentences yield roughly twice the error rate of Business. These results suggest that, in our evaluated offline setting under a strong LM prior, 3 keys are a practical minimum for general English.

Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth. Current decoding-time compression methods mitigate this issue via token eviction, but typically assume a uniform budget distribution across all layers and heads. In contrast, existing non-uniform budget allocation methods are predominantly designed for the static prompt prefill phase, and they do not capture the stepwise context demands of autoregressive reasoning. To bridge this gap, we propose ReasonAlloc, a training-free framework that recasts decoding-time KV compression as a hierarchical budget allocation problem. ReasonAlloc operates at two complementary levels: an offline layer-wise preallocation strategy captures an architecture-driven demand pattern which we call ``\textit{Reasoning Wave}'', while an online head-wise strategy reallocates resources during decoding to information-rich heads based on real-time utility. Evaluations on mathematical reasoning benchmarks (MATH-500, AIME~2024) using DeepSeek-R1-Distill-Llama-8B, DeepSeek-R1-Distill-Qwen-14B, and AceReason-14B show that ReasonAlloc outperforms uniform-budget R-KV, SnapKV, and Pyramid-RKV (a baseline enforcing a static, monotonically decreasing layer budget), with the largest gains at small budgets (128-512 tokens). ReasonAlloc is plug-and-play with existing token-eviction policies and introduces negligible inference-time overhead.

Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution. Serving these workloads requires scheduling, KV-cache management, and routing policies that use program-level context, including turn dependencies, tool-induced gaps, and reusable KV state. Evaluating such policies directly on real systems is costly, since each design point may require dedicated accelerator time across arrival rates, model scales, serving-instance counts, and memory hierarchies. Simulation offers a scalable alternative, but existing LLM serving simulators target stateless request-level workloads and therefore omit the core dynamics of agent serving: multi-turn program execution, cross-turn cache locality, and KV-cache residency during tool gaps. We present AGENTSERVESIM, a hardware-aware simulator for multi-turn LLM agent serving. AGENTSERVESIM evaluates serving policies at program granularity through composable modules: a Program Orchestrator preserves program identity and turn order, a Tool Simulator materializes tool-induced gaps, a Session-Aware Router maintains program-to-instance affinity for cache-aware dispatch, and a KV Residency Model tracks policy-defined KV placement across HBM, host DRAM/CXL, and eviction. Across real serving deployments and hardware configurations, AGENTSERVESIM reproduces real-system behavior within 6% error across key performance metrics while running entirely on commodity CPUs. These results show that AGENTSERVESIM enables controlled, repeatable exploration of agent-serving policies without requiring exhaustive deployment on costly accelerators.

Linear attention reformulates sequence modeling as recurrent state evolution, enabling efficient linear-time inference. Under the key-value associative paradigm, existing approaches restrict the role of the query to the readout operation, decoupling it from state evolution. We show that query-conditioned state readout induces a structured value prediction over accumulated memory that complements key-based retrieval. Based on this insight, we propose Q-Delta, a query-aware delta rule that integrates mixed key-query prediction errors into state evolution, enabling jointly corrective dynamics while preserving delta-rule efficiency. We establish stability guarantees for the resulting dynamics and derive a hardware-efficient chunkwise-parallel formulation with a custom Triton implementation. Empirical results demonstrate stable optimization, competitive throughput, and consistent improvements over strong baselines on language modeling and long-context retrieval tasks.

Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality generation with substantially fewer decoding steps. However, existing VAR models suffer from significant attention complexity and severe memory overhead due to the accumulation of key-value (KV) caches across scales. In this paper, we tackle this challenge by introducing KV cache compression into the next-scale paradigm. We begin with an in-depth analysis of VAR attention and observe that attention heads can be stably divided into two functionally distinct categories: Contextual Heads focus on maintaining semantic consistency, while Structural Heads preserve spatial coherence. Their functional divergence makes existing one-size-fits-all compression methods perform poorly on VAR models. We further find that the two head types differ markedly in their reliance on historical scales, and that this reliance shifts across layers and generation steps, arguing for an adaptive cache budget allocation. To address these challenges, we propose HACK++, a training-free Head-Aware key-value Compression frameworK for VAR models. From a one-time offline calibration, HACK++ classifies head types and derives head-specific priors. At inference, it decouples attention from cache compression under independent budgets, bounding the current-scale attention cost while compressing the accumulated cache far more aggressively, via pattern-specific strategies and a reliance-aware budget allocation. Extensive experiments on multiple VAR models across text-to-image, class-conditional, and unified understanding-and-generation tasks validate the effectiveness and generalizability of HACK++. For example, on Infinity-2B/8B, HACK++ maintains near-lossless generation with only a 30% attention budget and a 10% cache budget, and remains robust even under a 1% cache budget.

Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (KV) caches often dominates time-to-first-token (TTFT). Moreover, reusing caches across heterogeneous models (e.g., base and fine-tuned variants) causes semantic misalignment that accumulates over layers, degrading generation quality. We propose Semantic Cache Distillation (SCD), a loss-constrained framework that replaces raw KV transmission with compact semantic codes. SCD addresses these challenges via two mechanisms: (1) Reuse, which reconstructs most layers from low-rank subspaces to minimize transfer cost, and (2) Patch, which predicts normalized inputs at sparse transition layers to truncate error propagation. Empirically, SCD delivers up to 2.65 $\times$ TTFT speedup over the oracle consumer prefill and dominates quantization and selective recomputation baselines on the quality--latency Pareto frontier in bandwidth-constrained regimes, while keeping generation quality within 5% F1 of the oracle.

Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory -- not compute -- the binding constraint on throughput. Non-uniform KV compression, which allocates heterogeneous budgets across attention heads, preserves accuracy far better than uniform schemes, yet remains impractical: modern serving stacks assume identical KV lengths across heads, so heterogeneity traps freed memory as page fragmentation, spends up to 25% of prefill time reclaiming scattered pages, and skews GPU workloads that inflate decode latency by up to $1.7\times$ or burn 15--20% of each decode step on re-planning. We observe that this heterogeneity need not be discovered at runtime: head-wise retention follows a two-level structural regularity -- an input-invariant head ranking with narrowly bounded per-head ratios -- that can be calibrated offline from as few as 50 samples. Building on this insight, we present Tangram, a serving framework that statically resolves what prior systems handle dynamically: Budget Reservation fixes each head's post-compression footprint at scheduling time, eliminating page reclamation; Ragged Paging clusters similar-budget heads into independent page tables, turning fragmentation into reclaimable memory; and Ahead-of-Time Load Balancing precomputes balanced GPU partitions with zero runtime planning. Implemented on vLLM, Tangram serves as a drop-in substrate for existing non-uniform compression methods, matching their accuracy while improving end-to-end throughput by up to $2.6\times$ over the full-KV baseline. Our implementation is publicly available at https://github.com/aiha-lab/TANGRAM.

Large Language Models can reason over long contexts, yet prefilling millions of tokens is wasteful as much of the content remains static across queries. Cartridges address this by distilling document collections into reusable key-value (KV) caches that eliminate prefilling while preserving accuracy. A critical limitation of this approach is that cartridges are monolithic and non-compositional: encoding an entire collection into a single KV block does not scale, and naively mixing cartridges trained in isolation collapses performance to near chance. We introduce Cartridges at Scale (CAS), a training framework for scalable multi-cartridge learning with dynamic distractor mixing and a memory-efficient budget manager that rotates hundreds of per-document cartridges between GPU and persistent storage. Our approach scales to collections exceeding a million tokens, improving over a monolithic cartridge by 10-31 points at comparable token budgets. Oracle cartridge accuracy falls within 2-6 points of full in-context learning even at high compression. When paired with retrieval for cartridge selection, CAS matches or exceeds conventional RAG accuracy while consuming 3-4x fewer prompt tokens.

Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate inference, resulting in memory consumption that scales linearly with context length. This issue is particularly pronounced in VLMs due to substantial redundancy in the visual modality. Although KV cache eviction approaches can effectively reduce inference memory, they often incur significant performance degradation in VLMs, as most are designed for language models and overlook the inherent gap between text and vision. By systematically analyzing the modality gap in VLMs in this work, we argue that the importance of visual information should be grounded in textual guidance and accordingly propose a Text-Grounded KV Eviction method for VLMs (TGV-KV). TGV-KV comprises three submodules: (1) Text-Vision Budgeting (TVB) assigns budget to each layer based on the mutual information interaction. (2) Text-Weighted Ranking (TWR) assesses the priority of text and ranks vision importance based on weighted text-image attention. (3) Text-Prioritised Retention (TPR) policy strategically preserves text KV to avoid acute information loss. We evaluate TGV-KV across five models with different sizes and architectures, showing that TGV-KV preserves 99.2% full-KV accuracy on the VizWiz-VQA task with LLaVA-NeXT and boosts end-to-end throughput by 52.6% with an extreme retention budget of 5%. Code is available at https://github.com/Danielement321/TGV-KV.

Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role. However, the individual contribution of these three projections and the impact of omitting some remain poorly understood. We systematically evaluate three projection sharing constraints: a) Q-K=V (shared key-value), b) Q=K-V (shared query-key), and c) Q=K=V (single projection). The last two variants produce symmetric attention maps; to address this, we also explore asymmetric attention via 2D positional encodings. Through experiments spanning synthetic tasks, vision (MNIST, CIFAR, TinyImageNet, anomaly), and language modeling (300M and 1.2B parameter models on 10B tokens), we discovered that our transformers perform on par or occasionally better than the QKV transformer. In language modeling, Q-K=V projection sharing achieves 50% KV cache reduction with only 3.1% perplexity degradation. Crucially, projection sharing is complementary to head sharing (GQA/MQA): combining Q-K=V with GQA-4 yields 87.5% cache reduction, while Q-K=V + MQA achieves 96.9%, enabling practical on-device inference. We show that Q-K=V preserves quality because keys and values can occupy similar representational spaces and attention operates in a low-rank regime, whereas Q=K-V breaks attention directionality. Our results systematically characterize projection sharing as an underexplored instance of weight tying in attention, with direct, quantifiable inference memory benefits, particularly valuable for edge deployment. The code is publicly available at https://github.com/Brainchip-Inc/Do-Transformers-Need-3-Projections

Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized semantics from table-local evidence alone. Existing encoders model parts of this problem, but often underuse column-level value distributions and apply uniform objectives across attributes with different semantic roles. We propose NAVI, a segment-centric pretraining framework that treats each header-value pair as the unit for aggregating schema-level structural evidence and column-level distributional evidence. We realize this design through Masked Segment Modeling and Entropy-driven Segment Alignment, which jointly enforce structured header-value coupling and semantic alignment across stable and instance-specific attributes. Experiments on heterogeneous in-domain tables show improved reconstruction, semantic consistency, and downstream utility across evaluation settings overall.

Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measuring perplexity and accuracy without assessing the safety impact. In this study, we explore alignment preservation under KV cache quantization. Across eleven instruction-tuned models (3.8B-72B) and five benchmarks (1,894 prompts), we find that low-bit quantization can silently destroy safety alignment: Mistral-7B loses 15.2% of its refusals at only 1.03x perplexity, and no universal safe bit-width exists, with sharp model-specific phase transitions invisible to standard metrics. We identify that the root cause is geometric: safety features occupy a low-dimensional activation subspace 10^2-10^3x more vulnerable to quantization noise than the full representation space perplexity averages over. Inspired by this observation, we propose Per-Channel Reduction (PCR), a diagnostic that classifies each model into one of three mechanistic failure modes: outlier-crushes-safety, where safety lives in non-outlier channels collaterally damaged by outlier-driven scale factors; outlier-as-safety, where safety overlaps outlier channels and finer granularity cannot rescue it; and multi-layer dilution, where safety is distributed across many layers and per-layer fixes fail. PCR predicts the correct mitigation direction on all nine primary models and one held-out model from an independent family using 20 calibration prompts. PCR generalizes across unseen prompts, models, and production quantizers, including KIVI with up to 97.2% recovery, succeeding where attention-based allocation methods fail. The resulting training-free protocol, requiring approximately 35 GPU-minutes, recovers up to 97% of lost alignment at minimal memory overhead, addressing vulnerabilities confirmed in production vLLM serving with FP8 KV cache on NVIDIA GPUs.

Modern KV cache management assumes the chatbot workload: prompts arrive once and the cache grows append-only, so prefix caching and forward-only eviction are correct by construction. Agentic LLMs break this assumption. Their conversations evolve through policy-driven editing: failed tool calls are retried, stale outputs dropped, trajectories pivoted. Two distinct cache problems result. First, identical content moves to new positions between turns, invalidating exact-prefix caches even though the underlying KV would still be valid; recent work on position-independent caching for MLA addresses this reuse problem. Second, and this paper's focus, a policy may need to direct the serving system to actively remove or replace a span of cached content and continue without re-prefilling everything that came after. No existing primitive offers this. Production agentic harnesses fall back to re-prefill on every edit, paying full prefix-recomputation cost; kernel-level eviction methods make their own decisions and cannot accept policy directives from outside the kernel. We introduce Leyline, a serving-side primitive that closes this gap. A declarative directive 4-tuple separates what to edit from how to preserve position correctness. The policy declares the edit and its mode (in-place splice or prefix-trimmed re-prefill for semantic forgetting); an architecture-agnostic interface routes to a per-architecture kernel that restores attention math via a closed-form RoPE-rotation correction. The splice kernel lifts replay cache-hit by +11.2 pp and cuts latency by up to 241 ms. A ten-line truncation rule routed through the same interface lifts agentic solve rate by +14.3 pp on debug-gym. The mechanism is open; the policy space it enables is the agenda.

Diffusion Large Language Models (DLMs) have demonstrated significant advantages across various tasks. However, constrained by their multi-step iterative inference mechanism, their computational overhead and inference latency in long-context tasks have become core bottlenecks restricting their large-scale deployment. When processing long sequences, existing Key-Value (KV) caching mechanisms often face a dilemma where generation quality degrades drastically, where the core challenge lies in precisely and efficiently filtering critical tokens within ultra-long contexts. Inspired by the human reading process, we propose \textbf{WaveFilter}, a universal and training-free caching framework. This framework innovatively introduces the wavelet transform for decomposition of long sequences to achieve precise identification of key tokens, based on which a sparse KV Cache is constructed to compute the final contextual representation. Experimental results demonstrate that WaveFilter, as a plug-and-play generic framework, significantly enhances the performance of existing mainstream KV Cache methods in complex long-context tasks.

Transformers and deep state space models (SSMs) sit at opposite ends of a basic design choice: attention routes each query through a growing key-value (KV) cache by content-based matching at quadratic cost, while deep SSMs compress context into a fixed-size recurrent state that is not directly addressed by query-key matching. We propose Interdomain Attention, which integrates an SSM into an attention module through kernel methods: an attention kernel is approximated by a finite feature map, the resulting key features and values are projected onto a shared set of basis functions maintained by a single SSM recurrence, and each query attends to the compressed coefficients through its own feature map, recovering query-conditioned attention over a fixed-size state. The scalable layer is a learned relaxation of this derivation, and we validate its components through ablations. In a 125M to 1.3B autoregressive language-modeling study on FineWeb-Edu at matched recurrent-state budget, Interdomain Attention improves on an SSM token mixer at every scale, surpasses a same-recipe softmax baseline at 1.3B on validation perplexity and on the eight-task commonsense suite, and inherits the length-flat behavior of its fixed-state core out to 3.5x the training context. Ablations indicate that the query-conditioned projection is the main source of the gain.

AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties such as consistency between reads and writes must hold under every possible interleaving of events. Mechanized formal verification can guarantee such correctness, but typically demands months to years of expert effort. As evidence, even SOTA coding agents (Codex with GPT-5.4 and Claude Code with Opus 4.6) succeed on only 2/7 distributed key-value-store specifications. In this paper, we present the first effective approach to addressing this gap, Inductive Deductive Synthesis (IDS), which jointly and incrementally synthesizes implementation and proof, and learns from failed attempts to systematically try promising strategies. Built as an agentic LLM system, IDS achieves 7/7 in about 6.8 hours and $106 per spec on average, roughly 200x faster than expert effort and 17% cheaper than SOTA agents. IDS further incorporates performance feedback into the same loop, yielding implementations up to 3x faster than published verified systems.

The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when they process long contexts. Current KV Cache eviction has become an important research direction; however, existing methods based on fixed Soft Tokens (e.g., Judge Q) rely on a static parameter set as the query to evaluate the importance of KV pairs, so they cannot adapt dynamically to different input prompts, and they cannot precisely capture complex and changing task relevance. Also, evicted KV pairs are discarded permanently, so this causes irreversible information loss and context breaks. To address this problem, we propose Meta-Soft, a dynamic compression framework based on probe-driven context integration. Specifically, we build a meta-library with a learnable orthogonal basis matrix $\mathcal{L}$, and we use a selector network with Gumbel-Softmax to produce differentiable sparse combination weights, so we dynamically synthesize the most targeted $k$ Soft Tokens from the input prompt features. We append these Soft Tokens to the end of the input sequence to probe key information. We also introduce an attention-flow based integration mechanism, which redistributes the semantic information of removed tokens into retained tokens, and this keeps the dropped context information effectively. Experiments on multiple datasets show that our method outperforms existing state-of-the-art eviction methods and provides a new solution for KV Cache compression.

Long streaming video QA remains challenging due to growing visual tokens and limited reasoning length of large language models (LLMs). KV-caching stores the Key-Value (KV) of the historical tokens via LLM prefill and enables more efficient streaming QA. However, existing methods cache every one or two frames, causing redundant memory usage and losing fine-grained spatial details within frame or temporal contexts across frames. This paper proposes MuKV, a method that features a multi-grained KV cache compression module and a semi-hierarchical retrieval approach to improve both efficiency and accuracy for long streaming VideoQA. For the offline KV cache, MuKV extracts visual representations at patch-, frame-, and segment-levels. The multiple levels of granularity preserve both local cues and global temporal context, while maintaining efficiency with a dual signal token compression mechanism guided by self-attention and frequency. For online QA, MuKV designs a semi-hierarchical retrieval method to retrieve relevant KV caches for answer generation. Experiments on long-streaming VideoQA benchmarks show that MuKV significantly improves answer accuracy, without sacrificing memory and online QA efficiency. Moreover, our compression mechanism alone brings consistent benefits across answer accuracy, memory, and QA efficiency over baselines, showcasing highly effective contribution.

The rapid advancement toward long-context reasoning and multi-modal intelligence has made the memory footprint of the Key-Value (KV) cache a dominant memory bottleneck for efficient deployment. While the established per-channel quantization effectively accommodates intrinsic channel-wise outliers in Key tensors, its efficacy diminishes under extreme compression. In this work, we revisit the inherent limitations of the per-channel quantization paradigm from both empirical and theoretical perspectives. Our analysis identifies Token Norm Imbalance (TNI) as the primary bottleneck to quantization fidelity. We demonstrate that TNI systematically amplifies errors when shared quantization parameters are required to span token groups exhibiting substantial norm disparities. Instead of relying on intricate quantization pipelines (e.g., TurboQuant), we propose OScaR (Omni-Scaled Canalized Rotation), an accurate and lightweight KV cache compression framework for X-LLMs (i.e., text-only, multi-modal, and omni-modal LLMs). Advancing the per-channel paradigm, OScaR employs Canalized Rotation followed by Omni-Token Scaling to mitigate TNI-induced sequence-dimensional variance both effectively and efficiently, further supported by our optimized system design and CUDA kernels. Extensive evaluations across X-LLMs show that OScaR consistently outperforms existing methods and achieves near-lossless performance under INT2 quantization, establishing it as a robust, low-complexity, and universal framework that defines a new Pareto front. Compared with the BF16 FlashDecoding-v2 baseline, our OScaR implementation achieves a notable up to 3.0x speedup in decoding, reduces memory footprint by 5.3x, and increases throughput by 4.1x. The code for OScaR is publicly available at https://github.com/ZunhaiSu/OScaR-KV-Quant.

We study KV cache eviction under a shared globally capped decode-time harness. Seven policies (LRU, H2O, SnapKV, StreamingLLM, Ada-KV, QUEST, Random) share a prompt-boundary vulnerability: without structural protection, they collapse to near-zero quality on six pure-transformer models (F1$\leq$0.064). Reserving 10% of cache at each boundary recovers 69--90% of the $C{=}2{,}048$ reference-ceiling quality on seven LongBench models at $C{=}256$ (13% retention); a ten-model panel spans 68--98%. An attention-mass pilot (Qwen2.5-3B, $N{=}30$) suggests why: the position-0 sink holds ${\sim}75\%$ of prefix mass, while other boundary tokens sit near ${\sim}0.41{\times}$ uniform expectation, so attention scorers retain the sink but still drop structurally critical tokens. With protection, simplified score-isolation variants are TOST-equivalent to LRU at $K{=}32$ ($Δ{=}0.02$); at $K{=}8$, attention policies pairwise converge yet beat LRU by 0.011--0.021 F1 across $C{=}256$ and $C{=}512$. Faithful Ada-KV/QUEST add ${\sim}0.03$--$0.04$ F1 on Mistral-7B and Phi-3.5 beyond simplified variants. A NIAH-32K regime-transfer pilot on Qwen3-4B (decode vs.\ prefill, $C{\in}\{512,2048\}$) shows near-identical protection lifts (ratio 0.99--1.00). At 64K, protection helps but recovery is modest; faithful per-head scoring matches full-cache ceiling on Gemma-3-4B at 6.3% retention only when the model already supports strong 64K retrieval without eviction. Overall: protection dominates; scoring differences are secondary once boundaries are guarded; per-head allocation gives a further modest gain.

KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring. We study seven mechanisms across these five families under matched mean cache on long-form mathematical reasoning (MATH-500~\cite{hendrycks2021math}) with two distilled-reasoning models (Qwen-7B and Llama-8B variants of DeepSeek-R1-Distill~\cite{deepseek2025r1}) at budgets $b \in \{64, 128\}$. All seven were rejected. We then propose $α$, a one-function modification to the TriAttention~\cite{mao2026triattention} retention scorer that replaces argmax-top-$k$ with greedy facility-location-inspired selection under a V-space redundancy penalty controlled by a single weight $λ$. A pre-registered protocol tunes $λ$ on a frozen development split and confirms on a disjoint held-out split; with $λ= 0.5$, $α$ clears Bonferroni on two of the four (model, budget) cells (Qwen $b{=}128$ and Llama $b{=}64$), no cell is significantly negative, and the pre-registered Branch~A triggers. The finding is asymmetric: a minimal scoring modification beat heavier structural redesigns in this regime, and the combined matched-memory, sympy-graded, held-out confirmation protocol is the evidence standard that made the asymmetry visible.

Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeated High Bandwidth Memory (HBM) streaming rather than arithmetic. Existing methods such as eviction, windowing, quantization, and offloading reduce footprint, but often leave the critical-path bottleneck only partially addressed, especially when compressed states must still be reconstructed into dense vectors during decoding. We present Spherical KV, a long-context inference method that treats KV allocation as a rate-distortion problem grounded in attention geometry for efficient decoding. The method is built on two ideas: (i) represent directional information cheaply in the decode hot loop, and (ii) allocate retention and precision according to estimated future utility. Its first component, Angle-Domain Attention (ADA), stores keys in a spherical parameterization consisting of a scalar radius and compact angle codes, and computes attention logits directly from these codes without reconstructing dense keys. This preserves a paged, block-local, fusion-friendly decode path and directly targets HBM traffic in realistic serving settings. Its second component, Rate-Distortion Retention (RDR), jointly chooses keep/drop decisions and precision tiers per token and head under a fixed budget, producing tier-homogeneous pages with lightweight metadata and coalesced reads. Together, ADA and RDR provide a deployment-oriented mechanism for reducing KV residency while preserving decode efficiency.

LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit payload crossing network and storage boundaries, making KV a dominant end-to-end bottleneck. Existing KV compression are typically static runtime configurations, despite production service context varies over time in workload mix, bandwidth, and SLO/quality budgets. As a result, a fixed choice can be suboptimal or even increase latency. We present \emph{KVServe}, the first service-aware and adaptive KV communication compression framework for disaggregated LLM serving: KVServe (1) unifies KV compression into a modular strategy space with new components and cross-method recomposition; (2) introduces Bayesian Profiling Engine that efficiently searches this space and distills a 3D Pareto candidate set, reducing $50\times$ offline search overhead; and (3) deploys a Service-Aware Online Controller that combines an analytical latency model with a lightweight bandit to select profiles under constraints and correct offline-to-online mismatch. Integrated into vLLM and evaluated across datasets, models, GPUs and networks, KVServe achieves up to $9.13\times$ JCT speedup in PD-separated serving and up to $32.8\times$ TTFT reduction in KV-disaggregated serving.

We present Key-Value Means ("KVM"), a novel block-recurrence for attention that can accommodate either fixed-size or growing state. Equipping a strong transformer baseline with fixed-size KVM attention layers yields a strong $O(N)$ chunked RNN, while adding only an insignificant number of new parameters. We train a transformer with a growable KVM cache and show it performs competitively on long-context tests with only subquadratic prefill time and sublinear state growth. KVM is implementable with standard operations and without custom kernels, and supports chunk-wise parallelizable training and prefill. It provides many of the benefits of both traditional transformers (expandable context memory, chunk-wise parallelizable training and prefill) and linear RNNs in a single unified package. It can be used on every layer, saving KV-cache memory, and allowing a continuous range of choices of prefill time complexity between $O(N)$ and $O(N^2)$. It can also be implemented in a hybrid solution in tandem with LRNN layers in place of traditional attention, to supplement the LRNN with improved sublinear memory growth context length usage and long context decoding. We release our code at https://github.com/featherless-ai/KVM-paper and trained models at https://huggingface.co/collections/featherless-ai/kvm-paper under the Apache 2.0 license.

Reinforcement Learning (RL) has emerged as a crucial paradigm for unlocking the advanced reasoning capabilities of Large Language Models (LLMs), encompassing frameworks like RLHF and RLAIF. Regardless of the specific optimization algorithm (e.g., PPO, GRPO, or Online DPO), online RL inherently requires an exploratory trajectory generation (rollout) phase. However, for long-context reasoning tasks, this rollout phase imposes a severe ``memory wall'' due to the exorbitant Key-Value (KV) cache footprint. While applying KV cache compression during rollouts mitigates this memory overhead, it induces a critical off-policy bias. Although modern KV compression is often nearly lossless during standard inference, even minuscule approximation errors are drastically amplified by the inherent instability of RL optimization. Specifically, the sampler generates responses under a sparse context, whereas the learner updates parameters using the full, dense context. Existing statistical solutions, such as importance reweighting, struggle to correct this magnified bias, suffering from high gradient variance and severe sample inefficiency.

Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at every layer and can clutter long interactions; activation steering is compact but typically weaker and does not support large structured reminders. We introduce memory inception (MI), a training-free method that steers in latent attention space by inserting text-derived key-value (KV) banks only at selected layers. Rather than materializing reminder content throughout the prompt cache, MI treats steering as selective KV allocation, injecting latent slots only where the model routes to them. On matched personality-steering tasks, MI gives the best overall control--drift trade-off, remaining competitive with prompting while consistently outperforming CAA. On updateable guidance, MI supports mid-conversation behavior shifts without rewriting the visible transcript, achieving the highest post-shift alignment on Qwen3. On structured reasoning, MI outperforms visible prompting on HARDMath and PHYSICS (10/12 subject$\times$mode cells), serving as proxies for structured reasoning in verifiable domains, while cutting content-matched KV storage by up to 118$\times$. These results position MI as a powerful steering method when guidance is persistent, structured, or expensive to keep in the visible transcript.

How many key-value associations can a $d\times d$ linear memory store? We show that the answer depends not only on the $d^2$ degrees of freedom in the memory matrix, but also on the retrieval criterion. In an isotropic Gaussian model for the stored pairs, we show that top-1 retrieval, where every signal must beat its largest distractor, requires the logarithmic model-size scale $d^2\asymp n\log n$. We prove that the correlation matrix memory construction, which stores associations by superposing key-target outer products, achieves this scale through a sharp phase transition, and that the same scaling is necessary for any linear memory. Thus the logarithm is the intrinsic extreme-value price of winner-take-all decoding. We next consider listwise retrieval, where the correct target need not be the unique top-scoring item but should remain among the strongest candidates. To formalize this regime, we propose the Tail-Average Margin (TAM), a convex upper-tail criterion that certifies inclusion of the correct target in a controlled candidate list. Under this listwise retrieval criterion, the capacity follows the quadratic scale $d^2\asymp n$. At load $n/d^2\toα$, we develop an exact asymptotic theory for the TAM empirical-risk minimizer through a two-parameter scalar variational principle. The theory has a rich phenomenology: in the ridgeless limit it yields a closed-form critical load separating satisfiable and unsatisfiable phases, and it predicts the limiting laws of true scores, competitor scores, margins, and percentile profiles. Finally, a small-tail extrapolation further leads to the conjectural sharp top-1 threshold $d^2\sim 2n\log n$.

Semi-structured information extraction (IE) from OCR-derived clinical reports is crucial for efficiently reconstructing patients' longitudinal medical histories. In practice, this scenario commonly involves three tasks: (i) field-header (key) discovery, (ii) key-conditioned question answering (QA), and (iii) end-to-end key-value pair extraction. However, existing evaluations often under-model two factors: heterogeneous and incompletely known key representations, and OCR-induced noise. This makes it difficult to assess model robustness in real-world settings. We present MedStruct-S, a benchmark specifically designed to evaluate these tasks under unknown keys and OCR noise. MedStruct-S contains 3,582 annotated real-world clinical report pages. Using MedStruct-S, we benchmark two representative paradigms: encoder-only sequence labeling with post-processing and decoder-only structured generation, covering four encoder-only and five decoder-only models spanning 0.11B to 103B parameters. Our results show that encoder-only models achieve the best performance for non-null-value key-conditioned QA despite being substantially smaller than decoder-only models. When comparing models of similar order of magnitude, encoder-only models still perform better overall. Without controlling for model scale, fine-tuned decoder-only models deliver the strongest overall results. These findings show that the benchmark provides a reliable and practical basis for selecting and comparing models across different semi-structured IE settings.

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.

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.

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.

Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency. Early Exit has emerged as a promising solution to accelerate inference by dynamically bypassing redundant layers. However, in decoder-only architectures, the efficiency of Early Exit is severely bottlenecked by the KV Cache Absence problem, where skipped layers fail to provide the necessary historical states for subsequent tokens. Existing solutions, such as recomputation or masking, either introduce significant latency overhead or incur severe precision loss, failing to bridge the gap between theoretical layer reduction and practical wall-clock speedup. In this paper, we propose River-LLM, a training-free framework that enables seamless token-level Early Exit. River-LLM introduces a lightweight KV-Shared Exit River that allows the backbone's missing KV cache to be naturally generated and preserved during the exit process, eliminating the need for costly recovery operations. Furthermore, we utilize state transition similarity within decoder blocks to predict cumulative KV errors and guide precise exit decisions. Extensive experiments on mathematical reasoning and code generation tasks demonstrate that River-LLM achieves 1.53 to 2.16 times of practical speedup while maintaining high generation quality.

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.

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.

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.

Context-heavy agents place substantial pressure on the key-value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system can keep GPUs utilized. We study 4-bit KV-cache compression for this setting, using TurboQuant-style rotation and codebook quantization as a quality anchor and vLLM FP8 KV caching as the deployment anchor. We report three contributions. First, we frame 4-bit KV caching around multi-round agent workloads where task quality, cache residency, and serving throughput must be measured jointly. Second, we describe the practical design choices needed to make the 4-bit path robust, including asymmetric K/V treatment, Walsh-Hadamard rotation, QJL removal, and block-scale variants. Third, we present serving optimizations on AMD GPUs, including optimized decode-attention kernels and UltraQuant, an FP4 approximation path that uses FP8 queries, FP4 KV tensors, UE8M0 group scales, and native scaled-MFMA support on CDNA4. On an adaptive-SLO replay of production Claude Code traces, UltraQuant sustains 2.71x (MiniMax-M2.5) and 4.38x (Qwen3-235B) the qualified-request throughput of the BF16 baseline, matching or exceeding hardware FP8 KV while using half the KV bytes. UltraQuant delivers its largest gains in long-context, high-concurrency, memory-constrained serving regimes.