Meta AI is sharing new research to reduce the latency of existing Vision Transformer (ViT) models without the need for additional training. Our approach, called Token Merging...
In a paper published in October 2022 — “DreamShard: Generalizable embedding table placement for recommender systems” — we focus on embedding table sharding, or how to place the...
In August, Meta launched the 2022 AI4AI Research request for proposals (RFP). Today, we’re announcing the winners of this award.
In May, Meta launched the 2022 AI System Hardware/Software Codesign request for proposals (RFP). Today, we’re announcing the winners of this award.
For August, we are spotlighting Murali Annavaram, professor of Electrical and Computer Engineering and Computer Science at the University of Southern California (USC) and Director...
Announcing the winners of the Mephisto Dataset Collection Tool request for proposals