LLM.int8(): 8-Bit Matrix Multiplication for Transformers at Scale Posted by ofirpress on Wednesday August 17, 2022 @12:26PM from the arxiv.org dept. https://arxiv.org/abs/2208.07339 ( 1 comment | 7 points | on HN )
More from the author about this at: https://twitter.com/Tim_Dettmers/status/1559892888326049792