arXiv · 2611.12304
Evolving Infra: Agent-Adaptive LLM Serving at Scale
Abstract
Agentic workloads are a major source of LLM inference demand. Existing prefill--decode (PD) disaggregated serving systems offer limited flexibility for runtime adaptation of compute allocation and KV cache management, and rely on coarse signals that only partly capture the diverse and dynamic agent workload. These limitations lead to load imbalance between prefill and decode nodes and eviction of KV caches that agents will reuse. We present Evolving Infra, an agent-adaptive serving framework that adapts compute allocation to agent workloads and KV cache management to agent context management at runtime. We decouple compute allocation from key--value (KV) cache management, allowing nodes to switch efficiently between prefill and decode. Building on this design, an online planner matches the PD split to workload composition, while an agent-aware distributed KV manager guides cache eviction and transfer with signals from agent context management. Across coding, math, and computer-use tasks with GLM-5.2 and Kimi K2.6 on up to 256 GB300 GPUs, Evolving Infra reduces mean end-to-end request latency and P95 TTFT by up to 4.1x and 14x over Dynamo, NVIDIA's production framework. We open-source the system implementation of Evolving Infra at https://github.com/mit-han-lab/EvolvingInfra.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Hao Kang, Weili Xu, Ziyang Li, Zheng Du, Hanchen Li, Tian Xia, Song Bian, Tushar Krishna, Huizi Mao, Ion Stoica, Song Han. 2026-11-12. Evolving Infra: Agent-Adaptive LLM Serving at Scale. https://searcharxiv.com/abs/2611.12304
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.