Optimizing AI Workloads with LLMD and Inference Gateway

Guests are Clayton Coleman and Rob Shaw. Clayton is a Core contributor to Kubernetes, the containerized cluster manager, and founding architect for OpenShift, the open source platform as a service. Clayton helped launch the shift to cloud native applications and the platforms that enable them. At Google my mission is to make Kubernetes and GKE the best place to run workloads, especially accelerated AI/ML workloads, and especially especially very large model inference at scale with the inference gateway and llm-d. Rob Shaw is an Engineering Director at Redhat and is a contributor to the vLLM project.

Do you have something cool to share? Some questions? Let us know:

- web: kubernetespodcast.com

- mail: kubernetespodcast@google.com

- twitter: @kubernetespod

- bluesky: @kubernetespodcast.com

• Kubernetes 1.34 is expected to release end of August

• Kubecrash.io: A platform Eng conference with a purpose

• CNCF top 30 project of 2025

• LLM-D

• KubeCon EU 25 Keynote: LLM-Aware Load Balancing in Kubernetes

• WG Serving

• vLLM

• Disaggregated Prefilling

• LWS: LeaderWorkerSet