RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse

arXiv:2609.33503 · cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Terminology

• KV cache — 12× in this paper · explained in 3 episodes
• Transformer — 11× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Retrieval-Augmented Generation — 6× in this paper
• KV cache reuse — 5× in this paper · explained in 2 episodes
• Position-Independent Caching — 4× in this paper
• RAG — 4× in this paper · explained in 3 episodes
• Tokenization — 3× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Edge AI — 1× in this paper · explained in 2 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Phi-4 Technical Report
• KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
• Retrieval-Augmented Generation for Large Language Models: A Survey
• The Llama 3 Herd of Models
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation
• Qwen3 Technical Report
• KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse
• KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
• LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection