OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving

2026-09-12

AI Summary

OpWeave通过灵活的算子拆分和部署配置优化，解决了异构LLM服务中的硬件匹配和独立扩展问题，降低了服务成本。

Abstract

LLM serving systems increasingly disaggregate inference into finer-grained stages, with recent approaches separating attention from FFN or MoE execution during decode. This operator-level disaggregated serving (ODS) can improve hardware matching and enable independent scaling, particularly across heterogeneous devices. However, existing systems fix operator boundaries and lack a unified characterization of when disaggregation reduces serving cost. We present OpWeave, an end-to-end framework for heterogeneous ODS. OpWeave provides an analytical cost model that bounds the gains of homogeneous and heterogeneous ODS over colocated serving. It jointly optimizes operator partitioning and deployment configuration through a regularity-aware planner that keeps the search tractable even for hybrid-attention models. A vLLM-based runtime executes the synthesized plans with flexible operator stages across heterogeneous device groups. In our evaluation, OpWeave reduces serving cost by up to $1.78\times$ on homogeneous and $1.89\times$ on heterogeneous GPU clusters relative to the best feasible baseline, while meeting latency SLOs.

Problem

• operator disaggregation
• heterogeneous LLM serving
• hardware matching
• independent scaling
• cost model

Innovation

• Operator Disaggregation
• Heterogeneous LLM Serving
• Analytical Cost Model
• Regularity-aware Planner
• vLLM-based Runtime