Llumnix: Dynamic Scheduling for Large Language Model Serving.
Biao SunZiming HuangHanyu ZhaoWencong XiaoXinyi ZhangYong LiWei LinPublished in: CoRR (2024)
Keyphrases
- dynamic scheduling
- language model
- language modeling
- flexible manufacturing systems
- probabilistic model
- n gram
- retrieval model
- speech recognition
- document retrieval
- information retrieval
- language modelling
- mixture model
- ad hoc information retrieval
- context sensitive
- process planning
- test collection
- language models for information retrieval
- query terms
- query expansion
- statistical language models
- grid services
- relevance model
- smoothing methods
- language model for information retrieval
- query specific
- translation model
- loosely coupled
- relational databases
- digital libraries