WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More.
Yuxuan YueZhihang YuanHaojie DuanmuSifan ZhouJianlong WuLiqiang NiePublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- language modelling
- document retrieval
- retrieval model
- speech recognition
- query expansion
- test collection
- context sensitive
- statistical language models
- information retrieval
- vector space model
- ad hoc information retrieval
- spoken term detection
- language models for information retrieval
- document ranking
- weighting scheme
- pseudo relevance feedback
- query specific
- statistical language modeling
- query processing