Search papers, labs, and topics across Lattice.
University of California
3
0
6
NIXT transforms NCCL Inspector's data overload into clear, actionable insights, enabling researchers to pinpoint performance issues in large-scale model training.
Tri-serve redefines energy efficiency in multimodal inference by addressing hidden power inefficiencies, achieving a 22% boost without latency trade-offs.
OTRO reduces tokenizer latency to just 4.5% overhead while effectively safeguarding against side-channel attacks in LLMs.
