All People
MLT __init__ Paper Reading & Discussion Tim Dettmers, Mike Lewis, Younes Belkada, Luke Zettlemoyer: LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale.
Recent Activity1 x-posts
Recent Activity
Younes Belkada
@younesbelkada
Highlights: Younes Belkada co-authored the paper on LLM.int8() for 8-bit matrix multiplication, enabling large transformers to run with reduced memory.
Worth reading: This work is foundational for efficient deployment of large language models.
LLMInfraDeployment
1 x-posts · All time