all AI news
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale. (arXiv:2208.07339v2 [cs.LG] UPDATED)
Nov. 11, 2022, 2:12 a.m. | Tim Dettmers, Mike Lewis, Younes Belkada, Luke Zettlemoyer
cs.LG updates on arXiv.org arxiv.org
Large language models have been widely adopted but require significant GPU
memory for inference. We develop a procedure for Int8 matrix multiplication for
feed-forward and attention projection layers in transformers, which cut the
memory needed for inference by half while retaining full precision performance.
With our method, a 175B parameter 16/32-bit checkpoint can be loaded, converted
to Int8, and used immediately without performance degradation. This is made
possible by understanding and working around properties of highly systematic
emergent features in …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote