Optimizing Mixture of Experts using Dynamic Recompilations

4 May 2022

Papers citing "Optimizing Mixture of Experts using Dynamic Recompilations"

2 / 2 papers shown

Title
Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs Ferdi Kossmann Bruce Fontaine Daya Khudia Michael Cafarella Samuel Madden 116 2 0 23 Oct 2024
Scaling Laws for Neural Language Models Jared Kaplan Sam McCandlish T. Henighan Tom B. Brown B. Chess R. Child Scott Gray Alec Radford Jeff Wu Dario Amodei 264 4,489 0 23 Jan 2020