Fine-grained scaling for LLM inference on Red Hat OpenShift: The promise of DRASunyanan ChoochotkaewTatsuhiro Chiba2026Red Hat Summit 2026Talk
Dynamic Resource Allocation in Kubernetes: A New Paradigm for Device Allocation and Sharing Beyond GPUsLionel JouinSunyanan Choochotkaew2026FOSSASIA Summit 2026Talk
Share with Care: Efficient Device Sharing with Guaranteed Resources using DRASunyanan ChoochotkaewJohn Belamaric2025Kubecon + CloudNativeCon NA 2025Talk
Generative Computing Research and the Power of Open Source Sunyanan Choochotkaew2025SMARTCOMP 2025Keynote
Reimagining Cloud-Native Networks: The Critical Role of DRASunyanan ChoochotkaewLionel Jouin2025KubeCon Japan 2025Talk
Cloud Native Communities in Action: How Japan Shaped Its Path to KubeConNoriaki FukuyasuYuichi Nakamuraet al.2025KubeCon EU 2025Talk
Fit-to-Serve: How a New DRA Capability for Dynamic Device Sharing Fits into Distributed LLM ServingSunyanan ChoochotkaewTatsuhiro Chiba2025Cloud Native + Kubernetes AI Day 2025Talk
Predicting LLM Inference Latency: A Roofline-Driven ML MethodSaki ImaiRina Nakazawaet al.2024NeurIPS 2024Workshop paper