Leveraging Speculative Sampling and KV-Cache Optimizations Together for Generative AI using OpenVINO.
Haim BaradEkaterina AidovaYury GorbachevPublished in: CoRR (2023)
Keyphrases
- artificial intelligence
- generative model
- expert systems
- query processing
- random sampling
- sampling strategy
- sample size
- discriminative learning
- sampling algorithm
- prefetching
- parameter space
- knowledge based systems
- data driven
- knowledge representation
- ai community
- ai technologies
- monte carlo
- hit rate
- case based reasoning
- knowledge base
- markov chain monte carlo
- ai systems
- data sets
- sampling methods
- transmission line
- john mccarthy
- lecture notes in artificial intelligence
- data access
- main memory
- intelligent systems
- probabilistic model
- machine learning