IMI: In-memory Multi-job Inference Acceleration for Large Language Models.
Bin GaoZhehui WangZhuomin HeTao LuoWeng-Fai WongZhi ZhouPublished in: ICPP (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- speech recognition
- document retrieval
- language modelling
- information retrieval
- statistical language models
- retrieval model
- query expansion
- context sensitive
- language models for information retrieval
- smoothing methods
- pseudo relevance feedback
- query terms
- ad hoc information retrieval
- vector space model
- test collection
- mixture model
- relevance model
- bayesian networks
- machine learning
- document length
- language model for information retrieval
- passage retrieval
- translation model
- term dependencies
- error rate