LoongServe: Efficiently Serving Long-context Large Language Models with Elastic Sequence Parallelism.
Bingyang WuShengyu LiuYinmin ZhongPeng SunXuanzhe LiuXin JinPublished in: CoRR (2024)
Keyphrases
- language model
- context sensitive
- language modeling
- n gram
- information retrieval
- probabilistic model
- document retrieval
- retrieval model
- speech recognition
- smoothing methods
- language modelling
- ad hoc information retrieval
- statistical language models
- test collection
- query expansion
- relevance model
- translation model
- document ranking
- context dependent
- pseudo relevance feedback
- probabilistic retrieval models