DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression

arXiv:2610.06286 · cs.CL · Submitted 2026-10-05 · Read on arXiv

cs.CL

Submitted: 2026-10-05

Updated: 2026-10-05

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• KV cache — 1× in this paper · explained in 3 episodes

Sources

• LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• Mistral 7B
• ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
• GPT-4 Technical Report
• Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption
• The Llama 3 Herd of Models
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering