Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Taghibakhshi, Ali, Sreenivas, Sharath Turuvekere, Muralidharan, Saurav, Chochowski, Marcin, Karnati, Yashaswi, Joshi, Raviraj, Mahabaleshwarkar, Ameya Sunil, Chen, Zijia, Suhara, Yoshi, Olabiyi, Oluwatobi, Korzekwa, Daniel, Patwary, Mostofa, Shoeybi, Mohammad, Kautz, Jan, Catanzaro, Bryan, Aithal, Ashwath, Tajbakhsh, Nima, Molchanov, Pavlo
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.11409