How Visko streams real-time world models on Google Cloud TPUs
Publisher update
The brief
An interactive AI video stream has to generate each video chunk before playback catches up. Visko and Google Cloud report moving Orbis's video, upscaling and audio pipeline onto a single TPU slice, rendering at 1.07 times playback speed. Users can steer the ongoing scene with new prompts. This is a vendor/customer account of a specific deployment, not an independent performance benchmark.
Oct 29, 12:49 UTC Resolved - This incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.
In this SIG Architecture spotlight we talked with Janet Kuo (Google) and Yuan Tang (TensorScale AI) about the journey of AI Conformance in Kubernetes, from the initial Working Group to the integration SIG Architecture as a subproject. Introductions Frederico Muñoz and Kirti Goyal (FK): Hi Janet, Yuan, and thank you for the opportunity to learn a bit more about AI Conformance. Can you tell us a bit about yourselves and how you got involved in Kubernetes? Janet Kuo: I'm a Senior Staff Software Engineer at Google and have been a Kubernetes maintainer since 2015, joining the community just as we were racing toward the 1.0 launch. I started my journey writing the core workload controllers that standardized how applications are orchestrated on Kubernetes. Today, I lead SIG Apps as a Co-chair & TL, and also lead the AI Conformance program.
Source KubernetesCC BY 4.0 · Publisher excerpt shortened and converted to plain text. Original source license applies.
Oct 28, 15:28 UTC Resolved - This incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.
Oct 27, 17:09 UTC Resolved - This incident has been resolved. Oct 27, 16:41 UTC Monitoring - We are continuing to monitor for any further issues. Oct 27, 16:34 UTC Identified - We are continuing to work on a fix for the issue.
@cloudflare/computer ↗︎ gives your agent a workspace to run code in. From v0.7.0, that code can resume after a deploy or crash, and pause on an external action, for example to approve a tool call. Resume interrupted runs Set onInterrupt: "replay" on WorkerJavaScriptBackend, or on a single run.
Source Cloudflare DevelopersCC BY 4.0 · Publisher excerpt shortened and converted to plain text. Original source license applies.
The Agents SDK has a new createAI function for the AI SDK and Pi AI. It unifies what workers-ai-provider and ai-gateway-provider did: Workers AI models, AI Gateway catalog models, dynamic routes, and vendor models, through the AI binding or an account id and API token. workers-ai-provider and ai-gateway-provider are now feature frozen and marked as deprecated. Please migrate at your convenience.
Source Cloudflare DevelopersCC BY 4.0 · Publisher excerpt shortened and converted to plain text. Original source license applies.