Topology-Aware Data Movement for Disaggregated GPU Inference

arXiv:2607.28633v1 Announce Type: new Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly. When prefill and decode run on separate GPU pools, the KV cache must be transferred between them. For a 70B model this is 2.6 GB per request, exceeding 100 GB/s aggregate at production scale. Yet DistServe, Splitwise, and Mooncake all use uniform RDMA, ignoring that bandwidth between two GPUs varies by 72x depending on their physical relationship: 900 GB/s via NVLink within a domain, 50 GB/s via InfiniBand across nodes, 12.5 GB/s via TCP across data centers. We design a topology-aware transfer orchestrator that discovers interconnect hi