EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction

arXiv:2610.00412 · cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/ljwljwljwljw/kvpress

Terminology

• KV cache — 1× in this paper · explained in 3 episodes
• Pruning — 1× in this paper · explained in 4 episodes

Sources

• RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction
• Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
• Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores
• Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning
• Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
• Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
• SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
• Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
• The Llama 3 Herd of Models
• Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices
• KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
• Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
• RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
• MoBA: Mixture of Block Attention for Long-Context LLMs
• Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction
• Qwen3 Technical Report
• No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision 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