为下一代大模型推理系统打造高保真仿真工具，支持混合专家与拆分架构。
Frontier: Simulating the Next Generation of LLM Inference Systems
- 从零构建仿真框架，统一建模集中式与分布式推理系统。
- 原生支持混合专家并行，可模拟跨集群专家调度与延迟隐藏流水线。
- 精度提升的算子模型，助力大规模推理系统设计与优化。
大型语言模型（LLM）推理正因混合专家（MoE）模型和解耦架构（如预填充/解码、注意力/前馈分离）而日益复杂，这些架构通过异构扩展实现高效性。现有仿真器多针对集中式密集模型设计，难以捕捉新兴范式的复杂系统动态。本文提出 Frontier，一款专为新范式从头设计的高保真仿真器。它提供统一框架，支持集中与分布式系统建模，并原生支持混合专家并行（EP）。可模拟跨集群专家路由与先进流水线策略以隐藏延迟。通过精细化算子模型提升仿真精度。Frontier 使社区能够规模化地设计与优化未来大模型推理系统。
原文摘要 · Abstract (English)
Large Language Model (LLM) inference is growing increasingly complex with the rise of Mixture-of-Experts (MoE) models and disaggregated architectures that decouple components like prefill/decode (PD) or attention/FFN (AF) for heterogeneous scaling. Existing simulators, architected for co-located, dense models, are unable to capture the intricate system dynamics of these emerging paradigms. We present Frontier, a high-fidelity simulator designed from the ground up for this new landscape. Frontier introduces a unified framework to model both co-located and disaggregated systems, providing native support for MoE inference with expert parallelism (EP). It enables the simulation of complex workflows like cross-cluster expert routing and advanced pipelining strategies for latency hiding. To ensure fidelity and usability, Frontier incorporates refined operator models for improved accuracy. Frontier empowers the community to design and optimize the future of LLM inference at scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。