# Topology-Aware Data Movement for Disaggregated GPU Inference

arXiv: https://arxiv.org/abs/2607.28633 · HTML: https://mlsanity.com/paper/2607.28633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 8 of 8)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache](https://mlsanity.com/paper/2401.02669/) (2024)
- [Blink: Fast and Generic Collectives for Distributed ML](https://mlsanity.com/paper/1910.04940/) (2019)
- [TPP: Transparent Page Placement for CXL-Enabled Tiered-Memory](https://mlsanity.com/paper/2206.02878/) (2022)

## Abstract (arXiv)

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 1.3 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 4.0 within a domain (1.8 TB/s on NVLink 5, widening the gap to 144x), 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 hierarchy at startup and selects optimal transport per transfer. Three mechanisms work together: (1) pipelined layer-by-layer transfer that overlaps transmission with ongoing prefill, hiding 76 to 100 percent of transfer latency behind computation depending on transport, with NVLink and PCIe transfers hidden entirely; (2) NVLink domain-aware placement for Mixture-of-Experts models that co-optimizes expert dispatch with KV cache locality; and (3) CXL 3.0 memory expanders as a shared overflow tier providing 6x capacity at 86x lower latency than NVMe. Full evaluation requires multi-node clusters with heterogeneous interconnects and CXL 3.0 hardware that is beyond academic resources and not yet available in GPU clouds. We present analytical bandwidth models, component implementations, and projected analysis across three architectures showing 3 to 18x transfer latency reduction over uniform RDMA.