Cover Image

Training-Free Exponential Context Extension via Cascading KV Cache

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Willette, Jeffrey, Lee, Heejun, Lee, Youngwan, Jeon, Myeongjae, Hwang, Sung Ju
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SEA: Sparse Linear Attention with Estimated Attention Mask
by: Lee, Heejun, et al.
Published: (2023)

ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
by: Datta, Debajyoti, et al.
Published: (2026)

A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention
by: Lee, Heejun, et al.
Published: (2024)

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
by: Willette, Jeffrey, et al.
Published: (2025)

Position as Probability: Self-Supervised Transformers that Think Past Their Training for Length Extrapolation
by: Lee, Philip Heejun
Published: (2025)

GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer
by: Cho, Junmo, et al.
Published: (2026)

CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
by: Wang, Luning, et al.
Published: (2024)

KV Cache Offloading for Context-Intensive Tasks
by: Bocharnikov, Andrey, et al.
Published: (2026)

FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
by: Liu, Guangda, et al.
Published: (2025)

Visualizing the loss landscape of Self-supervised Vision Transformer
by: Lee, Youngwan, et al.
Published: (2024)

OjaKV: Context-Aware Online Low-Rank KV Cache Compression
by: Zhu, Yuxuan, et al.
Published: (2025)

Robust Molecular Property Prediction via Densifying Scarce Labeled Data
by: Kim, Jina, et al.
Published: (2025)

OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration
by: Ma, Xinyue, et al.
Published: (2026)

SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
by: Lee, Chanuk, et al.
Published: (2026)

MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
by: Li, Kunxi, et al.
Published: (2025)

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
by: Lee, Heejun, et al.
Published: (2025)

TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference
by: Dzikanyanga, Gradwell, et al.
Published: (2026)

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
by: Shi, Dachuan, et al.
Published: (2025)

SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching
by: Zhu, Yuxuan, 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)

KVSculpt: KV Cache Compression as Distillation
by: Jiang, Bo, et al.
Published: (2026)

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle
by: Wang, Zihan, et al.
Published: (2026)

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
by: Baek, Jinheon, et al.
Published: (2026)

KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
by: Nadali, Alireza, et al.
Published: (2026)

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
by: Liu, Akide, et al.
Published: (2024)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
by: Wu, Wei, et al.
Published: (2024)

RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
by: Liu, Sihao, et al.
Published: (2026)

KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference
by: Tian, Yuxuan, et al.
Published: (2025)

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
by: Su, Zunhai, et al.
Published: (2025)

EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection
by: Zhou, Yuhao, et al.
Published: (2025)

KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing
by: Yang, Yifei, et al.
Published: (2024)

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

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

Quantization Dominates Rank Reduction for KV-Cache Compression
by: Salfati, Samuel
Published: (2026)

KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
by: Jegou, Simon, et al.
Published: (2026)

Beyond Speedup -- Utilizing KV Cache for Sampling and Reasoning
by: Xing, Zeyu, et al.
Published: (2026)

LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
by: Wang, Guangtao, et al.
Published: (2025)

When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
by: Jeong, Soyeong, et al.
Published: (2025)

Attention Is All You Need for KV Cache in Diffusion LLMs
by: Nguyen-Tri, Quan, et al.
Published: (2025)

KV Cache Transform Coding for Compact Storage in LLM Inference
by: Staniszewski, Konrad, et al.
Published: (2025)