讀紙 ReadPaper

由 Claude Code Max 翻譯的 AI 論文繁體中文版 · 101 篇

標籤 願望清單
篩選標籤： KV Cache 2 篇 × 清除
2604.15039v1 arXiv License Alibaba / Qwen Team

Prefill-as-a-Service：下一代模型的 KVCache 可跨資料中心傳輸

Prefill-as-a-Service KVCache of Next-Generation Models Could Go Cross-Datacenter

Ruoyu Qin, Weiran He, Yaoyu Wang, Zheming Li, Xinran Xu, Yongwei Wu, Weimin Zheng, Mingxing Zhang

LLMInferenceKV CacheDisaggregationHybrid Attention系統優化
arXiv 8
Teds Lin 許願
2504.19874v1 CC BY 4.0 Google Research, New York University, Google DeepMind

TurboQuant：具有近最優失真率的線上向量量化

TurboQuant Online Vector Quantization with Near-optimal Distortion Rate

Amir Zandieh, Majid Daliri, Majid Hadian, Vahab Mirrokni

向量量化KV CacheLLM推理近鄰搜尋資訊理論
arXiv 112
Liang-Hsun Huang 許願