AnchorKV: Anchor-Residual KV Cache Compression
Malik Khalaf, Yara Shamshoum, Nitzan Hodos, Yuval Sieradzki, Assaf Schuster
cs.LG, cs.CL
Submitted: 2026-08-03
Comments: Under review
Code: https://github.com/0xsero/turboquant
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
- Palu: Compressing KV-Cache with Low-Rank Projection
- Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
- CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective
- OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
- Landmark Attention: Random-Access Infinite Context Length for Transformers
- KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction
- The Llama 3 Herd of Models
- D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models
- Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
- TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
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