CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference

• URL: http://arxiv.org/abs/2602.20732v1
• Date: Tue, 24 Feb 2026 09:54:59 GMT
• Title: CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference
• Abstract summary: We propose textbfCHESS, an textitalgorithm-system co-design KV-cache management system.<n>textbf1.% of the KV cache, delivers low-context stable inference with up to textbf4.56$times$ higher throughput, and consistently outperforms other strong baselines.
• Score: 9.561727872677173
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily constrained by KV cache as context grows. Prior pruning methods are largely context-agnostic: their token selection ignores step-wise relevance and local semantics, which undermines quality. Moreover, their irregular accesses and selection overheads yield only limited wall-clock speedups. To address this, we propose \textbf{CHESS}, an \textit{algorithm-system co-design} KV-cache management system. Algorithmically, CHESS introduces a context-aware, hierarchical selection policy that dynamically reconstructs a coherent context for the current decoding. System-wise, coarse granularity selection eliminates expensive data movement, fully realizing practical acceleration from theoretical sparsity. Extensive evaluations demonstrate that CHESS surpasses Full-KV quality using only \textbf{1\%} of the KV cache, delivers low-latency stable inference with up to \textbf{4.56$\times$} higher throughput, and consistently outperforms other strong baselines. Code is available at \href{https://anonymous.4open.science/r/CHESS-9958/}{https://anonymous.4open.science/r/CHESS/}.

Related papers

• CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration [67.17709877327232]
  Cate KV is a hybrid KV cache method that retains only critical token information for consistent heads.<n>Cate KV reduces memory usage by up to $2.72times$ and accelerates decoding by $2.18times$ in single-sample inputs.
  arXiv  Detail & Related papers  (2026-08-31T06:02:37Z)
• HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression [11.40656413331368]
  Long-context LLM inference faces a fundamental conflict: head-adaptive compression algorithms offer superior accuracy by dynamically fluctuating memory budgets.<n>Yet modern inference engines demand rigid, static memory patterns to leverage Graphs and PagedAttention.<n>We resolve this Static-Dynamic'' mismatch with HARD-KV, a unified framework that bridges dynamic selection with rigid system constraints.
  arXiv  Detail & Related papers  (2026-06-27T09:36:37Z)
• You Only Index Once: Cross-Layer Sparse Attention with Shared Routing [61.29627714699688]
  Cross-layer sparse attention (A) is built on top of KV-sharing architectures such as YOCO.<n>A single indexer computes token-level top-k selection once and reuses the resulting index across layers.<n>Results show CLSA is both accurate and efficient, achieving up to 7.6x decoding speedup and 17.1x overall throughput improvement at 128K context.
  arXiv  Detail & Related papers  (2026-06-04T17:54:04Z)
• Kwai Summary Attention Technical Report [69.40814939510126]
  Long-context ability, has become one of the most important direction of next-generation Large Language Models.<n>Standard softmax attention exhibits quadratic time complexity with respect to sequence length.<n>We propose Kwai Summary Attention (KSA), a novel attention mechanism that reduces sequence modeling cost by compressing historical contexts.
  arXiv  Detail & Related papers  (2026-04-27T12:59:53Z)
• CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference [3.1255988998610307]
  Centroid-Scoring Attention (CSAttention) is a training-free sparse attention method optimized for high- throughput contexts.<n>It front-loads computation into a one-time offline prefill phase that can be amortized across multiple queries.<n>It consistently outperforms state-of-the-art sparse attention methods in both model accuracy and inference speed.
  arXiv  Detail & Related papers  (2026-03-30T01:42:29Z)
• BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection [21.177715869071793]
  Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning.<n>We propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection.<n>We show that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua.
  arXiv  Detail & Related papers  (2026-03-20T04:35:04Z)
• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• OjaKV: Context-Aware Online Low-Rank KV Cache Compression with Oja's Rule [54.37983890753086]
  We introduce OjaKV, a framework that integrates a strategic hybrid storage policy with online subspace adaptation.<n>OjaKV preserves crucial first and most recent tokens in full-rank, maintaining high-fidelity anchors for attention.<n>It applies low-rank compression by incrementally adapting the projection basis using Oja's algorithm for online principal component analysis.
  arXiv  Detail & Related papers  (2025-09-25T21:42:27Z)
• KVCompose: Efficient Structured KV Cache Compression with Composite Tokens [7.922206020386125]
  Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding.<n>We propose a simple, yet effective, KV cache compression framework based on attention-guided, layer-adaptive composite tokens.<n>Our method achieves significant memory reduction while preserving accuracy, consistently outperforming prior structured and semi-structured methods.
  arXiv  Detail & Related papers  (2025-09-05T14:58:24Z)
• Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference [56.71209737306054]
  We propose textbfActQKV, a training-free, textbfActivation-aware approach that dynamically determines probe-textbfQuery and leverages it to retrieve the relevant textbfKV pairs for inference.<n>Experiments on the Long-Bench and $infty$ Benchmarks demonstrate its state-of-the-art performance with competitive inference quality and resource efficiency.
  arXiv  Detail & Related papers  (2025-02-19T08:50:44Z)
• ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference [61.412894960600205]
  Large Language Models (LLMs) require significant GPU memory when processing long texts.<n>ChunkKV reimagines KV cache compression by treating semantic chunks as basic compression units.<n>Result: ChunkKV outperforms state-of-the-art methods by up to 8.7% in precision.
  arXiv  Detail & Related papers  (2025-02-01T03:49:47Z)
• TreeKV: Smooth Key-Value Cache Compression with Tree Structures [19.06842704338332]
  TreeKV is a training-free method that employs a tree structure for smooth cache compression.<n>It consistently surpasses all baseline models in language modeling tasks on PG19 and OpenWebText2.
  arXiv  Detail & Related papers  (2025-01-09T06:00:27Z)
• EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation [8.757777529568383]
  Current RAG systems often struggle when retrieval models fail to rank the most relevant documents.<n>We introduce EXIT, an extractive context compression framework.<n>Our evaluations show that EXIT consistently surpasses existing compression methods.
  arXiv  Detail & Related papers  (2024-12-17T05:38:27Z)
• SCBench: A KV Cache-Centric Analysis of Long-Context Methods [61.025422435235456]
  We introduce SCBench, a benchmark for evaluating long-context methods from a KV cachecentric perspective.<n>We provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs and Mamba-Attention hybrids.<n>Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n2) pre-filling perform robustly.
  arXiv  Detail & Related papers  (2024-12-13T17:59:52Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens.<n>Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.