Перейти к содержимому

EuroMLSys2025

Distributed-Systems

0:00 / 0:00

EuroMLSys2025

7 просмотров · 2 недели назад
Distributed-Systems
8 подписчиков
7 просмотров · 2 недели назад
Video presentation based on the research article titled ``Deferred prefill for throughput maximization in LLM inference'', co-authored by Moonmoon Mohanty, Gautham Bolar, Preetam Patil, UmaMaheswari Devi, Felix George, Pratibha Moogi, and Parimal Parag. Presented by Moonmoon Mohanty at 5th Workshop on Machine Learning and Systems(EuroMLSys), Rotterdam, Netherlands, Mar 31, 2025.