Cover Image

HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gao, Yizhao, Wei, Jianyu, Zhang, Qihao, Cheng, Yu, Chen, Shimao, Tang, Zhengju, Jiang, Zihan, Song, Yifan, Zhang, Hailin, Zhao, Liang, Yang, Bo, Wang, Gang, Cao, Shijie, Luo, Fuli
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sparse Attention across Multiple-context KV Cache
by: Cao, Ziyi, et al.
Published: (2025)

SparseX: Efficient Segment-Level KV Cache Sharing for Interleaved LLM Serving
by: Zhang, Quqing, et al.
Published: (2026)

Rectified Sparse Attention
by: Sun, Yutao, et al.
Published: (2025)

CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference
by: Wu, Guanlong, et al.
Published: (2026)

PureKV: Plug-and-Play KV Cache Optimization with Spatial-Temporal Sparse Attention for Vision-Language Large Models
by: Jiang, Zhonghua, et al.
Published: (2025)

Beyond KV Caching: Shared Attention for Efficient LLMs
by: Liao, Bingli, et al.
Published: (2024)

HieraSparse: Hierarchical Semi-Structured Sparse KV Attention
by: Wang, Haoxuan, et al.
Published: (2026)

Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
by: Dehghankar, Mohsen, et al.
Published: (2026)

SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
by: Wang, Hanrui, et al.
Published: (2020)

SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
by: Gao, Yizhao, et al.
Published: (2024)

CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction
by: Goel, Raghavv, et al.
Published: (2025)

SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression
by: S, Santhosh G, et al.
Published: (2025)

Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
by: Chu, Kexin, et al.
Published: (2025)

SALS: Sparse Attention in Latent Space for KV cache Compression
by: Mu, Junlin, et al.
Published: (2025)

A Composable Dynamic Sparse Dataflow Architecture for Efficient Event-based Vision Processing on FPGA
by: Gao, Yizhao, et al.
Published: (2024)

TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
by: Bian, Zhuohang, et al.
Published: (2026)

LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction
by: Zhou, Enshuai, et al.
Published: (2026)

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

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

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
by: Gao, Yizhao, et al.
Published: (2025)

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
by: He, Yefei, et al.
Published: (2024)

SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling
by: Ji, Xiaodong, et al.
Published: (2025)

LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important
by: Liang, Manlai, et al.
Published: (2025)

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression
by: Zhang, Jiebin, et al.
Published: (2024)

Accurate KV Cache Quantization with Outlier Tokens Tracing
by: Su, Yi, et al.
Published: (2025)

Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction
by: He, Mutian, et al.
Published: (2025)

KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction
by: Yuan, Aomufei, et al.
Published: (2025)

Efficient Sparse Attention needs Adaptive Token Release
by: Zhang, Chaoran, et al.
Published: (2024)

Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
by: Kim, Junhyuck, et al.
Published: (2024)

CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing
by: Wang, Yixuan, et al.
Published: (2025)

Sparser Block-Sparse Attention via Token Permutation
by: Wang, Xinghao, et al.
Published: (2025)

HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference
by: Zeng, Bowen, et al.
Published: (2026)

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

Sparse Prefix Caching for Hybrid and Recurrent LLM Serving
by: Shirokikh, Mikhail, et al.
Published: (2026)

HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs
by: Yang, Dongquan, et al.
Published: (2025)

HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation
by: Xin, Lei, et al.
Published: (2026)

BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference
by: Zhao, Junqi, et al.
Published: (2024)

Joint OAM Multiplexing and OFDM in Sparse Multipath Environments
by: Liang, Liping, et al.
Published: (2024)

In-context KV-Cache Eviction for LLMs via Attention-Gate
by: Zeng, Zihao, et al.
Published: (2024)

Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference
by: Adnan, Muhammad, et al.
Published: (2024)