News for hackers. Stuff that matters.

A comment on LLM.int8(): 8-Bit Matrix Multiplication for Transformers at Scale.

Re:LLM.int8(): 8-Bit Matrix Multiplication for Transformers ... by ofirpress on Wednesday August 17, 2022 @12:26PM (#32498405)
Cool new efficient inference method that saves 2x memory and does not degrade performance for large language models!

More from the author about this at: https://twitter.com/Tim_Dettmers/status/1559892888326049792

[ Parent | on HN ]

There are no comments on this comment yet.