A handbook on how Mixture of Experts actually works, from routing to expert parallelism

techNmak · x · 2026-09-15

The author compiled a comprehensive MoE handbook covering router logits, Top-k selection, expert weighting, load balancing, capacity and token dropping, router z-loss, dropless execution, total vs. active parameters, and expert parallelism — with worked examples referencing Mixtral, DeepSeek-V3, and Qwen3, all cited back to original papers and current implementations.

Related event: Developer's MoE Handbook Goes Viral: From Routing to Expert Parallelism(3 posts)→

Original post →

More from Research

Research channel →