牛哥精选 · 所有

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

📝 深度技术 arXiv 机器学习 2026-06-30

Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

提出预测-重用-修复机制，动态稀疏注意力加速长上下文LLM解码，降低推理延迟。

arXiv:2606.30389v1 Announce Type: new Abstract: Dynamic sparse attention (DSA) accelerates long-context LLM decoding by attending to only the top-K KV…

llm 稀疏注意力长上下文解码加速深度学习

📝 深度技术 arXiv AI 2026-05-27

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference

针对内存受限MoE大模型推理的优化方案，通过微调路由器实现专家重用，在Jetson Orin NX上获得1.77-1.99倍解码加速。

arXiv:2605.27081v1 Announce Type: cross Abstract: Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, r…

moe 推理优化路由器微调内存受限解码加速

🤖 AI·大模型 arXiv 机器学习 2026-05-26

EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture

利用高效向量量化架构大幅加速LLM解码，已获顶级会议ISCA 2026接收，为推理提速带来新思路。

arXiv:2605.24144v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved impressive performance across diverse domains but remain …

llm解码加速向量量化高效架构 isca 2026 大模型推理

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference

EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture

📅 日期