CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion.
Jiayi YaoHanchen LiYuhan LiuSiddhant RayYihua ChengQizheng ZhangKuntai DuShan LuJunchen JiangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- information retrieval
- document retrieval
- language modelling
- query expansion
- probabilistic model
- ad hoc information retrieval
- test collection
- context sensitive
- language model for information retrieval
- statistical language models
- mixture model
- translation model
- retrieval model
- information fusion
- multi sensor
- query terms
- vector space model
- pseudo relevance feedback
- query specific
- data fusion
- machine learning