Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Ma, Xuezhe, Xiaomeng Yang, Wenhan Xiong, Beidi Chen, Lili Yu, Hao Zhang, Jonathan May, Luke Zettlemoyer, Omer Levy, and Chunting Zhou. 2024. “Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length.” arXiv:2404.08801 [cs.LG]. arxiv.org/abs/2404.08801
BibTeX
@misc{ma2024megalodon,
title = {Megalodon: {{Efficient LLM}} Pretraining and Inference with Unlimited Context Length},
author = {Ma, Xuezhe and Yang, Xiaomeng and Xiong, Wenhan and Chen, Beidi and Yu, Lili and Zhang, Hao and May, Jonathan and Zettlemoyer, Luke and Levy, Omer and Zhou, Chunting},
year = 2024,
eprint = {2404.08801},
primaryclass = {cs.LG},
url = {https://arxiv.org/abs/2404.08801},
archiveprefix = {arXiv}
}