all AI news
AttentionStore: Cost-effective Attention Reuse across Multi-turn Conversations in Large Language Model Serving
April 1, 2024, 4:42 a.m. | Bin Gao, Zhuomin He, Puru Sharma, Qingxuan Kang, Djordje Jevdjic, Junbo Deng, Xingkun Yang, Zhou Yu, Pengfei Zuo
cs.LG updates on arXiv.org arxiv.org
Abstract: Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines for executing multi-turn conversations are inefficient due to the need to repeatedly compute the key-value (KV) caches of historical tokens, incurring high serving costs. To address the problem, this paper proposes AttentionStore, a new attention mechanism that enables the reuse of KV caches (i.e., attention reuse) across multi-turn conversations, significantly reducing the repetitive computation overheads. …
abstract arxiv attention compute conversations cost cs.cl cs.lg feature however humans key language language model language models large language large language model large language models llm llms the key through tokens type value
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Analyst (Digital Business Analyst)
@ Activate Interactive Pte Ltd | Singapore, Central Singapore, Singapore