QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Item #:

079017-3180

Details

DOI: https://doi.org/10.52202/079017-3180
Author(s): Dan Alistarh, Saleh Ashkboos, Pashmina Cameron, Maximilian Croci, James Hensman, Torsten Hoefler, Martin Jaggi, Bo Li, Amirkeivan Mohtashami
Pages: 100213-100240 (28 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-3180
Author(s): Dan Alistarh, Saleh Ashkboos, Pashmina Cameron, Maximilian Croci, James Hensman, Torsten Hoefler, Martin Jaggi, Bo Li, Amirkeivan Mohtashami
Pages: 100213-100240 (28 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)