About

Xunzhuo Liu

Building collective intelligence for LLM systems.

Xunzhuo Liu
Current Focus

My focus is bringing collective intelligence to LLM systems.

My current work connects semantic routing with the Workload-Router-Pool architecture: using workload signals, policy loops, and coordinated serving pools to optimize quality, cost, latency, privacy, and safety together.

  • It is still a good thinking game.
  • Designing system-level intelligence above LLMs.
  • Routing is shifting from traffic control to behavior control.
Recent Papers

Selected papers on routing, reasoning, and inference systems.

Browse full archive
Community Roles

Kubernetes AI Gateway WorkGroup

Co-Chair

Leading the community effort to define standards for AI Gateway in the Kubernetes ecosystem.

CNCF Ambassador

Fall 2023 Ambassador

Representing and promoting Cloud Native Computing Foundation projects and values globally.

Linux Foundation APAC Open Source Evangelist

2024 Program

Advocating for open source adoption and best practices across the Asia-Pacific region.

KubeCon Program Committee

KubeCon 2024 Hong Kong

Reviewing and selecting talks for one of the largest cloud-native conferences.

Primary Track

vLLM Semantic Router

Co-Founder

Signal-driven decision routing for mixture-of-modality deployments.