Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models.
Siyan ZhaoDaniel IsraelGuy Van den BroeckAditya GroverPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- statistical language models
- document retrieval
- probabilistic model
- information retrieval
- query expansion
- speech recognition
- language modelling
- vector space model
- test collection
- pseudo relevance feedback
- smoothing methods
- okapi bm
- language models for information retrieval
- retrieval model
- ad hoc information retrieval
- translation model
- query specific
- document length
- context sensitive
- relevance model
- web documents
- information retrieval systems
- document ranking
- cross lingual
- language model for information retrieval