Package smile.llm.cluster
package smile.llm.cluster
-
ClassDescriptionThe follower side of a multi-node model: connects to a
ClusterLeader, learns its ranks and the NCCL unique id, then executes every message the leader sends, in order, acknowledging each.Executes one message; the follower acknowledges it afterwards.What the leader tells a follower on connection.The control side of a multi-node model: the leader process owns the server and the engine, and every call that changes model state (bind, prefill, decode step, finish...) is mirrored to the follower processes, which hold the other ranks and execute the identical call so that the NCCL collectives of all ranks line up.Writes the arguments of a message.