InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management.
Wonbeom LeeJungi LeeJunghwan SeoJaewoong SimPublished in: OSDI (2024)
Keyphrases
- language model
- language modeling
- cache management
- document retrieval
- speech recognition
- information retrieval
- n gram
- statistical language models
- language modelling
- query expansion
- test collection
- probabilistic model
- retrieval model
- context sensitive
- relevance model
- document ranking
- generative model
- machine learning
- power consumption
- distributed object