implementation detail · filed under model architecture
MaxVio
An expert-imbalance metric that compares the peak load on any expert with the perfectly balanced mean.
Also called MaxVio metric.
- source
- 1
- model
- 1
- labs adopt it
- 0
- strongest
- evaluated
How sources treat it
One count per evidence span, weakest treatment to strongest.
evaluated 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
To quantify expert imbalance, we measure the MaxVio metric (DeepSeek-AI, 2025b) which calculates the peak load on any single expert compared to the perfectly balanced mean.
evaluatedevaluation onlyin Nemotron 3 UltraNVIDIA
Filed alongside
Other methods under model architecture :: channel mixer :: mixture of experts :: expert load balancing.
Auxiliary-loss-free load balancingQuantile BalancingHistogram-based quantile estimationAuxiliary-loss load balancingExact coordinate minimizationExpert bias update factorExpert Parallelism Load BalancingExponential moving average of estimated quantilesformHCLoad balancingModality-specific auxiliary-loss-free load balancingPersistent load balancingPooled-global-batch quantile estimationRound-robin load balancing