Muon optimizer doubles first MoE layer bias span
Muon raises router bias span in early MoE layers, complicating load balancing at tuned learning rates.
1 stories, newest first · one card per story
Muon raises router bias span in early MoE layers, complicating load balancing at tuned learning rates.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views