Close

Presenter

Arya Mazaheri
Technical University Darmstadt
Presentations
Paper
PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
Accelerators
Artificial Intelligence/Machine Learning
Cloud Computing
Distributed Computing
Heterogeneous Computing
Performance Optimization
TP
Posters
PipeInfer: Accelerating LLM Inference Using Asynchronous Pipelined Speculation​
TP
XO/EX