o ˜à·iXã@s,ddlmZmZddlZGdd„deƒZdS)é)ÚABCÚabstractmethodNc@sVeZdZee d dejdededededejdBdeejejejffd d „ƒƒZ dS) ÚAbstractEplbPolicyNÚweightÚ num_replicasÚ num_groupsÚ num_nodesÚ num_ranksÚold_global_expert_indicesÚreturncCst‚)a  Entry point for expert-parallelism load balancer. Parameters: weight: [layers, num_logical_experts], the load statistics for all logical experts num_replicas: number of physical experts, must be a multiple of `num_ranks` num_groups: number of expert groups num_nodes: number of server nodes num_ranks: number of ranks, must be a multiple of `num_nodes` old_global_expert_indices: [layers, num_logical_experts], the old global expert indices. Used to avoid unnecessary weight copying for experts moving within one rank. Returns: physical_to_logical_map: [layers, num_replicas], the expert index of each replica logical_to_physical_map: [layers, num_logical_experts, X], the replica indices for each expert expert_count: [layers, num_logical_experts], number of physical replicas for each logical expert )ÚNotImplementedError)Úclsrrrrr r ©rú[/home/ubuntu/vllm_env/lib/python3.10/site-packages/vllm/distributed/eplb/policy/abstract.pyÚrebalance_experts s!z$AbstractEplbPolicy.rebalance_experts)N) Ú__name__Ú __module__Ú __qualname__Ú classmethodrÚtorchÚTensorÚintÚtuplerrrrrr s&ùþýüûúùør)ÚabcrrrrrrrrÚs