70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)

Item #:

085713-3306

Details

DOI: https://doi.org/10.52202/085713-3306
Author(s): Tianyi Zhang, Mohsen Hariri, Shaochen (Henry) Zhong, Vipin Chaudhary, Yang Sui, Xia Hu, Anshumali Shrivastava
Pages: 109696-109724 (29 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/085713-3306
Author(s): Tianyi Zhang, Mohsen Hariri, Shaochen (Henry) Zhong, Vipin Chaudhary, Yang Sui, Xia Hu, Anshumali Shrivastava
Pages: 109696-109724 (29 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)