CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving.
Yuhan LiuHanchen LiYihua ChengSiddhant RayYuyang HuangQizheng ZhangKuntai DuJiayi YaoShan LuGanesh AnanthanarayananMichael MaireHenry HoffmannAri HoltzmanJunchen JiangPublished in: SIGCOMM (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- speech recognition
- retrieval model
- information retrieval
- data streams
- query expansion
- language modelling
- test collection
- smoothing methods
- context sensitive
- ad hoc information retrieval
- query processing
- document ranking
- query terms
- word error rate
- document length
- statistical language models
- word clouds
- translation model
- multiword
- query specific
- mixture model
- language model for information retrieval