PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU.
Yixin SongZeyu MiHaotong XieHaibo ChenPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- document retrieval
- query expansion
- retrieval model
- language modelling
- probabilistic model
- information retrieval
- ad hoc information retrieval
- test collection
- statistical language models
- mixture model
- context sensitive
- pseudo relevance feedback
- query terms
- smoothing methods
- document ranking
- query specific
- language modeling framework
- hidden markov models