Efficient Memory Management for Large Language Model Serving with PagedAttention.
Woosuk KwonZhuohan LiSiyuan ZhuangYing ShengLianmin ZhengCody Hao YuJoseph GonzalezHao ZhangIon StoicaPublished in: SOSP (2023)
Keyphrases
- language model
- memory management
- language modeling
- n gram
- speech recognition
- probabilistic model
- document retrieval
- statistical language models
- language modelling
- retrieval model
- operating system
- context sensitive
- relevance model
- efficient implementation
- smoothing methods
- ad hoc information retrieval
- language model for information retrieval
- query expansion
- information retrieval
- test collection
- mixture model
- word clouds
- hardware implementation
- translation model
- machine learning
- query terms