EarlySelectKV: Anticipatory KV Selection via Cross-Layer Query Proxies
cs.CL
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/sea-with-sakura/EarlySelectKV
Terminology
Sources
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- The Llama 3 Herd of Models
- Mistral 7B
- Qwen2.5 Technical Report
- Fast Transformer Decoding: One Write-Head is All You Need
- ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data