Views
No views yet
./<dmodel>/<n_experts>/<n_att_heads>/<n_training_steps>.pt../benchmark.py.@misc{ludziejewski2025jointmoescalinglaws,
title={Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient},
author={Jan Ludziejewski and Maciej Pióro and Jakub Krajewski and Maciej Stefaniak and Michał Krutul and Jan Małaśnicki and Marek Cygan and Piotr Sankowski and Kamil Adamczewski and Piotr Miłoś and Sebastian Jaszczur},
year={2025},
eprint={2502.05172},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2502.05172},
}