Search Results for author: Yinsicheng Jiang

Found 1 papers, 0 papers with code

MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems

no code implementations10 Dec 2024 Yao Fu, Yinsicheng Jiang, Yeqi Huang, Ping Nie, Zhan Lu, Leyang Xue, Congjie He, Man-Kit Sit, Jilong Xue, Li Dong, Ziming Miao, Kai Zou, Edoardo Ponti, Luo Mai

Its key innovation is a sparsity-aware CAP analysis model, the first to integrate cost, performance, and accuracy metrics into a single diagram while estimating the impact of sparsity on system performance.

Benchmarking

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