{"type":"post","id":"google-cloud-publishes-open-ai-native-stack-on-e79e26","slug":"google-cloud-publishes-open-ai-native-stack-on-e79e26","title":"Google Cloud publishes open AI-native stack on Kubernetes: OpenRL, llm-d 1.0, KubeRay on GKE","description":"Google Cloud’s November 10, 2026 announcement describes an open-source Kubernetes stack for RL post-training, distributed inference, Ray workloads and agent execution.","retrieval_nugget":"Google Cloud’s November 10, 2026 announcement describes an open-source Kubernetes stack for RL post-training, distributed inference, Ray workloads and agent execution. For teams running open-weight models on GKE, the practical proposition is coordinated resource use and cache-aware serving; Google reports specific performance gains, but they are company-reported results rather than independent validation.","published_at":"2026-11-14","updated_at":"2026-11-14","record_date":"2026-11-14","date_kind":"published_at","topics":["google"],"entities":["Google Cloud","OpenRL","llm-d","KubeRay","GKE","Agent Substrate","gVisor","TorchTPU"],"related_patterns":["harness-architecture-outlives-model-choice","agent-security-moves-to-runtime-boundaries"],"novelty_label":"new_fact","what_changed":"Google Cloud outlines a broader open AI-native Kubernetes stack, adding OpenRL, KubeRay on GKE, and agent components alongside llm-d 1.0.","prior_refs":["https://newruntime.com/posts/announcing-llm-d-1-0-open-distributed-inference-7539eb/"],"source_url":"https://cloud.google.com/blog/topics/developers-practitioners/the-open-ai-native-stack-on-kubernetes-from-open-models-to-distributed-inference-and-agents","source_urls":["https://cloud.google.com/blog/topics/developers-practitioners/the-open-ai-native-stack-on-kubernetes-from-open-models-to-distributed-inference-and-agents"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:google-cloud-publishes-open-ai-native-stack-on-e79e26","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/google-cloud-publishes-open-ai-native-stack-on-e79e26/","markdown":"https://newruntime.com/posts/google-cloud-publishes-open-ai-native-stack-on-e79e26.md","json":"https://newruntime.com/posts/google-cloud-publishes-open-ai-native-stack-on-e79e26.json"},"markdown_url":"https://newruntime.com/posts/google-cloud-publishes-open-ai-native-stack-on-e79e26.md","next_reads":[{"type":"topic","path":"/topics/google/","url":"https://newruntime.com/topics/google/","title":"Google","reason":"Explore the google topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/google.md","json_url":"https://newruntime.com/topics/google.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}