SGD-KV: Summarization Guided KV Cache Compression

arXiv:2609.03235 · cs.CL · Submitted 2026-09-03 · Read on arXiv

cs.CL

Submitted: 2026-09-03

Updated: 2026-09-03

Comments: Accepted in NeurIPS2026 Efficient Reasoning Workshop

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

Terminology

• KV cache — 55× in this paper · explained in 3 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Aggregation — 7× in this paper · explained in 1 episode
• Generalization — 4× in this paper · explained in 13 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Attention Mechanism — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought (CoT) Reasoning — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• OpenAI Multi-Round CoReference Resolution — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes

Sources

• Qwen2.5-1M Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
• Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
• ETHIC: Evaluating Large Language Models on Long-Context Tasks with High Information Coverage
• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
• SnapKV: LLM Knows What You are Looking for Before Generation
• Qwen3 Technical Report
• Llama-Nemotron: Efficient Reasoning Models
• LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
• Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization

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