vix.ing · top · new · best · stats · spec

Jack Chang

  1. Scalable Training of Mixture-of-Experts Models with Megatron Core
    2026/03/08 by Zijie Yan, Hongxiao Bai, Xin Yao +42 · 3 voices · 2 citations
    #cs.DC #cs.CL #cs.LG