@online{huang2025optimizations,
  author       = {Huang, Xuanqiang Angelo},
  title        = {Optimizations for {DNN}},
  date         = {2025-06-03},
  organization = {Xuanqiang Angelo Huang's Blog},
  url          = {https://flecart.github.io/notes/optimizations-for-dnn/},
  langid       = {english},
  abstract     = {Mixture of Experts \# There is a gate that opens a subset of the experts, and the output is the weighted sum of the outputs of the experts. The weights are computed by a gating network. One problem is load balancing, non uniform assignment. And there is a lot of communication over}
}