Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-prefill aggregation, to prefill-decode (P/D) disaggregation, and most recently to operator-level Attention-FFN Disaggregation (AFD). This trend is especially important for mixture-of-experts (MoE) models, where memory-bound attention, compute-intensive expert FFNs, and MoE dispatch/combine communication create distinct resource demands. AFD further exposes this heterogeneity by placing attention and MoE-FFN execution on separate GPU groups. Each level of disaggregation deepens the scheduling design space across workload characteristics, resource allocation, and interconnect topology, raising the central question: when does each level actually pay off? We systematically characterize this trade-off for MoE inference across realistic workloads spanning input/output sequence lengths, prefix-KV reuse, and per-user latency constraints. Using chunked-prefill and P/D disaggregation as baselines, we study the benefits and limits of AFD at scale through a framework that fuses on-device kernel measurements with high-fidelity network simulation. Under strict TTFT/TPOT SLOs, AFD sustains around 4k tokens/s of system throughput on DeepSeek-V3.2 across chat, coding, and agentic-coding workloads, where non-AFD deployments are infeasible. We distill concrete takeaways for jointly optimizing throughput and interactivity, including how to partition attention and FFN across GPUs as a function of workload and model architecture, providing design principles for current rack- and cluster-scale deployments as well as future disaggregated AI infrastructure.

翻译：现代大语言模型推理已逐步走向解聚，以应对日益增长的模型规模以及严格的TTFT和TPOT服务等级目标：从分块预填充聚合，到预填充-解码解聚，直至最新的算子级Attention-FFN解聚趋势。这一趋势对于混合专家模型尤为重要：其中受内存限制的注意力机制、计算密集型的专家FFN以及MoE分发/合并通信产生了截然不同的资源需求。AFD通过将注意力机制和MoE-FFN执行分布在单独的GPU组上，进一步暴露了这种异构性。每一级解聚都深化了涵盖工作负载特征、资源分配和互连拓扑的调度设计空间，从而引出一个核心问题：每种解聚方式何时真正带来收益？我们针对覆盖输入/输出序列长度、前缀KV缓存复用及单用户延迟约束的实际工作负载，系统性地刻画了MoE推理中的这一权衡。以分块预填充和P/D解聚为基线，我们通过融合设备内核测量与高保真网络模拟的框架，研究了大规模部署下AFD的优势与局限。在严格的TTFT/TPOT SLO约束下，AFD在DeepSeek-V3.2上针对聊天、编程和智能编程工作负载可维持约4000 tokens/s的系统吞吐量，而未经AFD的部署方案在此场景下不可行。我们提炼出了联合优化吞吐量与交互性的具体结论，包括如何依据工作负载和模型架构在GPU间划分注意力与FFN，为当前机架级和集群级部署以及未来解聚式AI基础设施提供了设计原则。