Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV Caches

arXiv:2610.09827 · cs.LG · Submitted 2026-10-07 · Read on arXiv

cs.LG

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

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

Sources

• Palu: Compressing KV-Cache with Low-Rank Projection
• Evaluating Large Language Models Trained on Code
• SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
• Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms
• The Llama 3 Herd of Models
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
• SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
• GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
• Ministral 3
• Qwen3 Technical Report
• Post-Training Sparse Attention with Double Sparsity
• OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks