--- format: "aidr-story-markdown/v1" id: "1f766ec7b68d14d4ac5de7486b912910152af255545b6d1690f4cddd0f70f301" canonical_url: "https://aidr.today/1f766ec7?lang=en" title: "Build a Validated Kubernetes Runtime for NVIDIA Dynamo" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-30T21:35:31.000Z" category: "Tools" topics: ["nvidia","inference","devtools"] source_urls: ["https://developer.nvidia.com/blog/build-a-validated-kubernetes-runtime-for-nvidia-dynamo/"] summary: "NVIDIA's AI Cluster Runtime (AICR) packages the NVIDIA Dynamo distributed inference framework and supporting infrastructure into validated recipes for Kubernetes deployments. Each recipe defines configurations for specific environments and workloads, including pinned component versions, compatibility constraints, and validation checks. AICR provides platform teams with a repeatable way to deploy and validate the runtime, offering developers a consistent foundation for serving models and testing applications." --- # Build a Validated Kubernetes Runtime for NVIDIA Dynamo > [Open the canonical story]() **Published:** 2026-10-30T21:35:31.000Z **Category:** Tools **Topics:** nvidia, inference, devtools ## Summary NVIDIA's AI Cluster Runtime \(AICR\) packages the NVIDIA Dynamo distributed inference framework and supporting infrastructure into validated recipes for Kubernetes deployments\. Each recipe defines configurations for specific environments and workloads, including pinned component versions, compatibility constraints, and validation checks\. AICR provides platform teams with a repeatable way to deploy and validate the runtime, offering developers a consistent foundation for serving models and testing applications\. ## Sources - [Story source]()