About

I am nobody.

I study the intelligent routing.

Current Focus

I focus on bringing collective intelligence to the LLM systems:

  • vLLM Semantic Router
    Co-Founder
    System Level Intelligent Router for Mixture-of-Models.
    GitHub | Website | Papers

Selected Works

I have worked on the following projects:

  • Envoy Gateway
    Steering Committee & Maintainer
    Manages Envoy Proxy as a Standalone or Kubernetes-based Application Gateway.
    GitHub | Website

  • Envoy AI Gateway
    Maintainer
    Manages Unified Access to Generative AI Services built on Envoy Gateway.
    GitHub | Website

  • vLLM AIBrix
    Maintainer
    Cost-efficient and pluggable Infrastructure components for GenAI inference.
    GitHub | Website

  • Istio
    Maintainer
    Connect, secure, control, and observe services.
    GitHub | Website

  • Kiali
    Maintainer
    Observability console for Istio with service mesh.
    GitHub | Website

  • Aeraki Mesh
    Maintainer
    Manage any layer-7 protocols in a Service Mesh.
    GitHub | Website

  • Merbridge
    Maintainer
    Use eBPF to speed up your Service Mesh.
    GitHub | Website

  • Higress
    Committer
    AI Gateway & AI Native API Gateway.
    GitHub | Website

  • Kubernetes Gateway API
    Reviewer
    Role-oriented, portable, and expressive interfaces for Kubernetes networking.
    GitHub | Website

  • Kubernetes Ingress2Gateway
    Reviewer
    Convert Ingress resources to Gateway API resources.
    GitHub | Website

Community Roles & Recognition

  • Kubernetes AI Gateway WorkGroup
    Co-Chair
    Leading the community effort to define standards for AI Gateway in 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 Asia-Pacific region.

  • KubeCon Program Committee
    KubeCon 2024 Hong Kong
    Reviewing and selecting talks for one of the largest cloud-native conferences.