DeltaZip: Multi-Tenant Language Model Serving via Delta Compression.
Xiaozhe YaoAna KlimovicPublished in: CoRR (2023)
Keyphrases
- language model
- multi tenant
- language modeling
- n gram
- data center
- document retrieval
- probabilistic model
- information retrieval
- language modelling
- retrieval model
- mixture model
- test collection
- speech recognition
- query expansion
- context sensitive
- ad hoc information retrieval
- cloud computing
- statistical language models
- smoothing methods
- pseudo relevance feedback
- sensor networks
- query specific