VFold: Symmetry-Aware Cross-Layer Value Cache Compression

arXiv:2610.12338 · cs.CL, cs.LG · Submitted 2026-10-08 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/nverma1/vfold

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

Terminology

• Alignment — 39× in this paper · explained in 1 episode
• KV cache — 30× in this paper · explained in 3 episodes
• Quantization — 15× in this paper · explained in 12 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Cosine Similarity — 8× in this paper · explained in 3 episodes
• Large Language Model — 7× in this paper
• Pruning — 6× in this paper · explained in 4 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Canonical Correlation Analysis — 4× in this paper
• Calibration — 3× in this paper · explained in 7 episodes
• Grouped Query Attention — 3× in this paper
• Centered Kernel Alignment — 2× in this paper
• Model Merging — 2× in this paper · explained in 2 episodes
• Needle In A Haystack — 2× in this paper
• Redundancy — 2× in this paper · explained in 2 episodes
• Transformer Models — 2× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
• Ministral 3
• CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing
• Qwen3 Technical Report
• KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing

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