Search Results for author: Yingdi Shan

Found 1 papers, 0 papers with code

Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation

no code implementations • 3 May 2024 • Shaoyuan Chen, Wencong Xiao, Yutong Lin, Mingxing Zhang, Yingdi Shan, Jinlei Jiang, Kang Chen, Yongwei Wu

To enhance the efficiency of LLM decoding, we introduce model-attention disaggregation.

Language Modeling Language Modelling +2

Paper
Add Code

Cannot find the paper you are looking for? You can Submit a new open access paper.