AttentionStore: Cost-effective Attention Reuse across Multi-turn Conversations in Large Language Model Serving.
Bin GaoZhuomin HePuru SharmaQingxuan KangDjordje JevdjicJunbo DengXingkun YangZhou YuPengfei ZuoPublished in: CoRR (2024)
Keyphrases
- cost effective
- language model
- language modeling
- probabilistic model
- n gram
- low cost
- environmentally friendly
- test collection
- speech recognition
- cost effectiveness
- retrieval model
- language modelling
- document retrieval
- query expansion
- information retrieval
- statistical language models
- query terms
- mixture model
- ad hoc information retrieval
- context sensitive
- language models for information retrieval
- smoothing methods
- pseudo relevance feedback
- document ranking
- relevance model
- document length
- word error rate
- translation model
- speech signal
- retrieval effectiveness
- co occurrence
- language model for information retrieval