Pack n weighted objects to m packs, such that each bin contains exactly n/m objects and the weights of all packs are as balanced as possible.

Parameters: weight: [num_moe_layers, num_logical_experts] num_physical_experts: number of physical experts after replication

Replicate `num_log` experts to `num_phy` replicas, such that the maximum load of all replicas is minimized. Parameters: weight: [X,

Entry point for expert-parallelism load balancer. Parameters: weight: [layers, num_logical_experts], the load statistics for all log