One Queue Is All You Need: Resolving Head-of-Line Blocking in Large Language Model Serving.
Archit PatkeDhemath ReddySaurabh JhaHaoran QiuChristian PintoShengkun CuiChandra NarayanaswamiZbigniew KalbarczykRavishankar K. IyerPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- information retrieval
- document retrieval
- retrieval model
- language modelling
- context sensitive
- speech recognition
- test collection
- query expansion
- mixture model
- ad hoc information retrieval
- query terms
- language models for information retrieval
- pseudo relevance feedback
- vector space model
- document length
- statistical language models
- language model for information retrieval