GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs

arXiv:2605.31105 · cs.CL · Submitted 2026-05-29 · Read on arXiv

cs.CL

Submitted: 2026-05-29

Updated: 2026-08-31

Comments: Accepted by EMNLP 2026 Main

Code: https://github.com/pjunjie/GRKV

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

Terminology

• KV cache — 28× in this paper · explained in 3 episodes
• Regularization — 16× in this paper · explained in 3 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Consistency — 5× in this paper · explained in 3 episodes
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Few-Shot Learning — 5× in this paper · explained in 4 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Aggregation — 3× in this paper · explained in 1 episode
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Over-smoothing — 3× in this paper · explained in 4 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Anchor Tokens — 1× in this paper · explained in 1 episode
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes

Sources

• Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
• CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective
• Phi-4 Technical Report
• GPT-4 Technical Report
• The Llama 3 Herd of Models
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
• Palu: Compressing KV-Cache with Low-Rank Projection
• Mistral 7B
• CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing
• Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
• On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference
• Gemma 2: Improving Open Language Models at a Practical Size
• Qwen3 Technical Report
• LLaMA: Open and Efficient Foundation Language Models
• Llama 2: Open Foundation and Fine-Tuned Chat Models

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