Page-EntroKV: Hardware-Aligned, Entropy-Weighted KV-Cache Eviction under Grouped-Query Attention
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- Fast Transformer Decoding: One Write-Head is All You Need
- The Llama 3 Herd of Models
- Qwen2.5 Technical Report
- Mistral 7B
- SnapKV: LLM Knows What You are Looking for Before Generation
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
- InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
- Retrieval Head Mechanistically Explains Long-Context Factuality
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
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