Cover Image

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Jiwon, Jo, Dongwon, Kang, Beomseok, Kim, Jae-Joon
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
by: Jo, Dongwon, et al.
Published: (2025)

Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
by: Jo, Dongwon, et al.
Published: (2026)

LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning
by: Kang, Beomseok, et al.
Published: (2025)

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
by: Song, Jiwon, et al.
Published: (2025)

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference
by: Kang, Beomseok, et al.
Published: (2026)

RelayGen: Intra-Generation Model Switching for Efficient Reasoning
by: Song, Jiwon, et al.
Published: (2026)

Block-Attention for Efficient Prefilling
by: Ma, Dongyang, et al.
Published: (2024)

SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
by: Song, Jiwon, et al.
Published: (2024)

QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models
by: Jeon, Hyesung, et al.
Published: (2025)

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
by: Fan, Qihang, et al.
Published: (2026)

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache
by: Song, Dinghong, et al.
Published: (2025)

CLAA: Cross-Layer Attention Aggregation for Accelerating LLM Prefill
by: McDanel, Bradley, et al.
Published: (2026)

ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
by: Ye, Lu, et al.
Published: (2024)

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
by: Lu, Songshuo, et al.
Published: (2024)

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
by: Liu, Xiang, et al.
Published: (2025)

SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
by: Wu, Shunlong, et al.
Published: (2026)

BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
by: Song, Chenyang, et al.
Published: (2025)

Accelerating Prefilling via Decoding-time Contribution Sparsity
by: He, Zhiyuan, et al.
Published: (2025)

CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs
by: Lv, Junlin, et al.
Published: (2024)

SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation
by: Qiao, Aurick, et al.
Published: (2024)

Accelerating Prefilling for Long-Context LLMs via Sparse Pattern Sharing
by: Peng, Dan, et al.
Published: (2025)

PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
by: Woo, Sunghyeon, et al.
Published: (2026)

Adaptive Chunking: Optimizing Chunking-Method Selection for RAG
by: Júnior, Paulo Roberto de Moura, et al.
Published: (2026)

ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Management
by: Zou, Jing, et al.
Published: (2026)

SurfaceLogicKV: Surface and Logic Attention Behaviors are All You Need for Robust KV Cache Compression
by: Li, Mengjie, et al.
Published: (2025)

WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference
by: Zuo, Youhui, et al.
Published: (2025)

FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion
by: Hu, Zhanqiu, et al.
Published: (2025)

FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
by: Fan, Qihang, et al.
Published: (2026)

KV Shifting Attention Enhances Language Modeling
by: Xu, Mingyu, et al.
Published: (2024)

Optimizing Mixture of Block Attention
by: Xiao, Guangxuan, et al.
Published: (2025)

DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
by: Guo, Jinyu, et al.
Published: (2026)

G-KV: Decoding-Time KV Cache Eviction with Global Attention
by: Liao, Mengqi, et al.
Published: (2025)

HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing
by: Gao, Yizhao, et al.
Published: (2026)

KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head
by: Rehg, Isaac
Published: (2024)

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads
by: He, Xingyang, et al.
Published: (2025)

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
by: Li, Dongfang, et al.
Published: (2026)

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
by: Mao, Weian, et al.
Published: (2026)

GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction
by: Li, Xuelin, et al.
Published: (2025)

FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
by: Lai, Xunhao, et al.
Published: (2025)

SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block Size
by: Chen, Jinhan, et al.
Published: (2025)