Rita Zhang @ritazh.bsky.social · 23/03/2026It’s basically moving from 'it works on my cluster' to 'it’s ready for the product' in one step. 120
Rita Zhang @ritazh.bsky.social · 23/03/2026No Engine Lock-in: They can swap backends (vLLM, SGlang, LlamaCPP, etc.) without rewriting their deployment logic. Unified Lifecycle: If the rest of the company’s stack is on K8s, AI Runway lets them use the same observability, security, and CI/CD tools as everyone else. 110
Rita Zhang @ritazh.bsky.social · 23/03/2026Zero-to-Inference: Instead of writing complex Slurm scripts or wrapping models in custom Flask containers, AI Runway provides a standard interface to deploy LLMs with production-grade scaling and routing out of the box. 130
Rita Zhang @ritazh.bsky.social · 23/03/2026The pitch for AI Runway to AI/ML teams isn't about 'changing how you work,' but about 'removing the wall between your model and the user.' 120
Rita Zhang @ritazh.bsky.social · 23/03/2026AI Runway is aimed at platform teams and AI users who want a Kubernetes-native way to deploy and operate inference workloads across multiple serving frameworks, with a simpler UX and tighter integration with the Kubernetes ecosystem. 150
Rita Zhang @ritazh.bsky.social · 23/03/2026Maintainer for AI Runway here 👋. Slurm on Kubernetes is useful if you want HPC-style job scheduling, but it does not provide a common kubernetes inference API or a model-centric control plane. 020
Reposted by Rita ZhangBridget Kromhout @bridgetkromhout.bsky.social · 23/03/2026AI Runway as explained by @squillace.bsky.social at the #KubeCon Azure pre-day: deploy and manage large language models on Kubernetes. github.com/kaito-projec... 1113
Reposted by Rita ZhangBridget Kromhout @bridgetkromhout.bsky.social · 18/03/2026"Great to be at the #Dynamo #GTC2026 event seeing real-world adoptions and exciting to see Microsoft as one of the top external contributors to help strengthen the platform and grow the OSS community." @ritazh.bsky.social www.linkedin.com/posts/ritazh...linkedin.comHow NVIDIA Dynamo 1.0 Powers Multi-Node Inference at Production Scale | NVIDIA Technical Blog | Rita Zhang🚀 Huge milestone! Congrats to the NVIDIA team on Dynamo v1.0.0! Great to be at the #Dynamo #GTC2026 event seeing real-world adoptions and exciting to see Microsoft as one of the top external contribu... 054
Reposted by Rita ZhangInspektor Gadget @inspektor-gadget.io · 18/12/2025❄️Our holiday gift to you❄️ tcpdump for Kubernetes! In this blog we share how we've taken tcpdump to the next level with K8s context to make it easier than ever to debug networking issues - including with Wireshark! inspektor-gadget.io/blog/2025/12...inspektor-gadget.ioDebugging Kubernetes Network Issues with Inspektor Gadget's tcpdump Gadget | Inspektor GadgetDebugging Kubernetes Network Issues with Inspektor Gadget's tcpdump Gadget 031
Reposted by Rita ZhangBridget Kromhout @bridgetkromhout.bsky.social · 09/11/2025Ask the experts: Kubernetes Steering Committee at #KubeCon. Lots of good discussion about supporting contributors with @kat.lol @ritazh.bsky.social @soltysh.bsky.social. 0293
Reposted by Rita ZhangBridget Kromhout @bridgetkromhout.bsky.social · 09/11/2025At the Kubernetes AI Conformance discussion at #KubeCon Maintainer Summit, @ritazh.bsky.social talks about the value of collaborating across open source communities. github.com/kubernetes-s... 053
Reposted by Rita Zhangsquillace @squillace.bsky.social · 08/11/2025If you, ALSO, are motivated by superfast, hardware protected micro vms, this starts in 5 minutes! www.youtube.com/live/tROp-nm...youtube.comCloud Native Rejekts Atlanta 2025 (Crystal Dining Room) 2YouTube video by Cloud Native Rejekts 131
Reposted by Rita ZhangBridget Kromhout @bridgetkromhout.bsky.social · 28/10/2025New blog post: Scaling multi-node LLM inference with NVIDIA Dynamo and ND GB200 NVL72 GPUs on AKS (by Sachi Desai, @ritazh.bsky.social, & @sozercan.bsky.social) blog.aks.azure.com/2025/10/24/d...blog.aks.azure.comScaling multi-node LLM inference with NVIDIA Dynamo and ND GB200 NVL72 GPUs on AKS | AKS Engineering BlogLearn how optimizing routing, planning, and system setup boosts the efficiency and reliability of multi-node LLM inference on AKS with OSS Dynamo and ND GB200-v6 GPUs. 113
Reposted by Rita Zhangsquillace @squillace.bsky.social · 30/09/2025For those Master's or Ph.D. students doing systems work, you might have a look at this internship with @microsoft.com's research team: www.linkedin.com/posts/pedroh... Yes, you'll do some immediately important work, and it's really cool, too.linkedin.com🚀 Internship Opportunity in Systems Research The Microsoft Research - Systems Group https://lnkd.in/dPCb5fqC) and the Azure Research - Systems https://lnkd.in/dhf6Xx-s) are hiring an intern to help… ...🚀 Internship Opportunity in Systems Research The Microsoft Research - Systems Group https://lnkd.in/dPCb5fqC) and the Azure Research - Systems https://lnkd.in/dhf6Xx-s) are hiring an intern to help b... 043
Reposted by Rita ZhangBridget Kromhout @bridgetkromhout.bsky.social · 25/08/2025Interested in the upstream Kubernetes ecosystem? @lachie.bsky.social is hosting a new conversation series where he chats with an Azure colleague about exciting new topics in K8s! In the first episode, he discusses AI-aware Kubernetes infrastructure with Jack Francis! www.youtube.com/watch?v=7G-z...youtube.comAI-Aware Kubernetes Infrastructure - Upstream@AKS - Episode1 - Azure Kubernetes Service (AKS)YouTube video by Azure Kubernetes Service (AKS) 064
Reposted by Rita ZhangAaron Wislang 🇨🇦 @aaronw.dev · 14/08/2025Wassette: A bridge between Wasm and MCP by Simon Bisson (@sbisson.com) www.infoworld.com/article/4039...infoworld.comWassette: A bridge between Wasm and MCPMicrosoft’s new open-source tool kit offers a way to assemble lightweight and secure Model Context Protocol servers from WebAssembly components. 021
Reposted by Rita ZhangIan Coldwater 🧊🚫 @lookitup.baby · 14/08/2025github.comCVE-2025-5187: Nodes can delete themselves by adding an OwnerReference · Issue #133471 · kubernetes/kubernetesCVSS Rating: CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:L - Medium (6.7) A vulnerability exists in the NodeRestriction admission controller where node users can delete their corresponding node obje... 5477
Reposted by Rita ZhangDavid Flanagan @rawkode.bsky.social · 07/08/2025I'm super excited for Wassette, so I put together a quick article on why it's important and a comparison with our current options for MCP.rawkode.academyWassette: WebAssembly Security for AI AgentsWassette, a WebAssembly-based sandboxing technology for AI agent tools, and an analysis of why it represents a major step forward in security compared to traditional methods like Docker and direct exe... 1114
Reposted by Rita ZhangAaron Wislang 🇨🇦 @aaronw.dev · 06/08/2025Introducing Wassette: WebAssembly-based tools for AI agents by Yosh Wuyts opensource.microsoft.com/blog/2025/08...opensource.microsoft.comIntroducing Wassette: WebAssembly-based tools for AI agents - Microsoft Open Source BlogWassette is a secure, open-source Model Context Protocol server that leverages WebAssembly to provide a trusted execution environment for untrusted tools. 0106
Reposted by Rita ZhangKate Holterhoff, PhD @kateholterhoff.com · 20/05/2025TIL @microsoft.com is the largest cloud contributor to #oss @cncf.io projects #MSBuild 2248
Rita Zhang @ritazh.bsky.social · 15/04/2025Need to run really large LLMs that require the power of RDMA with InfiniBand? Check out this blog to see how to get it working on Azure Kubernetes Service: azure.github.io/AKS/2025/04/... #AKS #Kubernetes #InfiniBand #AI #LLM #RDMA #Azureazure.github.ioSimplifying InfiniBand on AKSLearn the what, the whys, and the hows of configuring InfiniBand networking for high performance compute (HPC) workloads on AKS 043
Reposted by Rita ZhangPhil Estes @estesp.dev · 03/04/2025The @containerd.dev maintainer session is underway at #KubeCon EU in London with an awesome cross-section of contributors and maintainers from both the core project and subprojects like nerdctl and runwasi. 1165
Rita Zhang @ritazh.bsky.social · 03/04/2025I will be there on behalf of sig auth and the k8s security response committee. See you there! #kubecon 270
Reposted by Rita ZhangKubernetes @kubernetes.io · 02/04/2025Day 2 of #KubeCon begins tomorrow! On Day 1, we learned from keynotes & sessions & enjoyed the #Kubecrawl party. We hope you're ready to do it all again tomorrow! Don't forget to stop by the Project Pavillion during lunch to meet the Kubernetes community!sched.coKubeCon + CloudNativeCon Europe 2025: Kubernetes SIG Meet & Greet Lunch and Le...View more about this event at KubeCon + CloudNativeCon Europe 2025 093
Reposted by Rita ZhangMicah Hausler @micahhausler.com · 02/04/2025Standing room only for the talk on Policy as code by @ritazh.bsky.social, Joe Betz, Andy Sunderman, and Jim Bugwadia 051
Reposted by Rita ZhangBridget Kromhout @bridgetkromhout.bsky.social · 02/04/2025OPA Gatekeeper (open-policy-agent.github.io/gatekeeper/) as explained by @ritazh.bsky.social at #KubeCon: tooling to help enforce your Kubernetes policies. 041
Reposted by Rita ZhangChris Aniszczyk @cra.dev · 02/04/2025huge fan of headlamp moving into kubernetes to improve the dashboard and devex experience for all k8s users! kudos @ahrkrak.bsky.social and team! #kubecon #cloudnativecon 02011
Reposted by Rita ZhangLiz Rice 💛💙🐝 @lizrice.com · 02/04/2025Fantastic to have Greg K-H on the #kubecon keynote stage! 0122
Rita Zhang @ritazh.bsky.social · 02/04/2025Making kubernetes easier to use. better UX = happier humans with @headlamp_ui #KubeCon keynote. Now part of sig UI @ahrkrak.bsky.social 0315
Rita Zhang @ritazh.bsky.social · 02/04/2025Dynamic Resource Allocation feature highlighted on the big stage #kubecon keynote 170
Rita Zhang @ritazh.bsky.social · 02/04/2025So many great CNCF projects are hitting the 10 year mark! So grateful to be part of the journey #kubecon 091
Reposted by Rita ZhangRita Zhang @ritazh.bsky.social · 28/03/2025If you are attending #KubeCon 🇬🇧next week, come and say hi! I will be co-presenting 2 talks: sched.co/1tcxh sched.co/1tczC 2174
Rita Zhang @ritazh.bsky.social · 29/03/2025Folks from the US traveling in London, if you have tmobile, can you tell me if the connection is good or spotty or slow? thanks 🙏 #kubecon 210
Rita Zhang @ritazh.bsky.social · 28/03/2025If you are attending #KubeCon 🇬🇧next week, come and say hi! I will be co-presenting 2 talks: sched.co/1tcxh sched.co/1tczC 2174
Reposted by Rita ZhangGiant Swarm @giantswarm.io · 28/03/2025🔥 Whoa! Check out these critical Ingress NGINX vulnerabilities that could impact your Kubernetes clusters. Curious about better gateway solutions? Our very own Marco Ebert will be sharing what we've learned building a Gateway API implementation on NGINX at #KubeCon!wiz.ioRemote Code Execution Vulnerabilities in Ingress NGINX | Wiz BlogWiz Research uncovered RCE vulnerabilities (CVE-2025-1097, 1098, 24514, 1974) in Ingress NGINX for Kubernetes allowing cluster-wide secret access. 021
Reposted by Rita Zhangsquillace @squillace.bsky.social · 26/03/2025Something I can't wait to talk about at #wasmio and @rejekts.io and at #kubecon: how to run #webassembly components at scale but with efficient hardware protection using #hyperlight. aka.ms/hyperlight-w...aka.msHyperlight Wasm: Fast, secure, and OS-free - Microsoft Open Source BlogWe're announcing the release of Hyperlight Wasm: a Hyperlight virtual machine “micro-guest” that can run wasm component workloads written in many programming languages. Learn more. 21712
Reposted by Rita ZhangDavid Justice @david.justice.dev · 26/03/2025Running #Wasm components inside of a hypervisor and being able to tailor the exact interface between the hosted application and the trusted compute base enables platform builders unequaled ability to tune precisely the access provided to untrusted application code. 1134
Reposted by Rita ZhangDavid Justice @david.justice.dev · 10/03/2025Delighted to see this post land! Learn how you can make a guest for Hyperlight to execute code in a secure sandbox with "Build a Hyperlight C guest to securely execute Javascript" opensource.microsoft.com/blog/2025/03...opensource.microsoft.comBuild a Hyperlight C guest to securely execute Javascript - Microsoft Open Source BlogThis article will show you how to create a “guest” application that uses the Hyperlight library and have fun with some JavaScript. Learn more. 166
Reposted by Rita ZhangJosh Duffney @joshduffney.bsky.social · 28/02/2025Overwhelmed by CVEs in container images? This series about Copacetic can help. 😊 123
Rita Zhang @ritazh.bsky.social · 17/02/2025Lego Card Dealing Machine youtu.be/ed9pLQLkCEM more details: ritazh.com/lego-card-deal… #lego #automation #petprojectyoutu.beLEGO Card Dealing MachineYouTube video by Rita Zhang 020
Reposted by Rita Zhangdanologue.bsky.social @danologue.bsky.social · 11/02/2025At #KubeConNA2024, we demoed super fast, hardware-protected micro-VMs with Hyperlight—executing untrusted code in just 900µs! Read how we achieved this & try the demo yourself: 🔗 opensource.microsoft.com/blog/2025/02... #RustLang #WebAssembly #CloudNative #MicroVMsopensource.microsoft.comHyperlight: Creating a 0.0009-second micro-VM execution time - Microsoft Open Source BlogIn this post, we’ll take the demo application and show how it demonstrates one way you can use Hyperlight in your applications. Learn more. 0106
Reposted by Rita ZhangDavid Justice @david.justice.dev · 03/02/2025Hey Folks, join us for our first public community meeting for github.com/hyperlight-d... on Wednesday Feb. 5th at 9am PT (dateful.com/convert/pst-...). You can find the join details and agent for the meeting here hackmd.io/blCrncfOSEuq.... Feel free to add topics. See you soon! #rust #hyperlightgithub.comGitHub - hyperlight-dev/hyperlight: Hyperlight is a lightweight Virtual Machine Manager (VMM) designed to be embedded within applications. It enables safe execution of untrusted code within micro virt...Hyperlight is a lightweight Virtual Machine Manager (VMM) designed to be embedded within applications. It enables safe execution of untrusted code within micro virtual machines with very low latenc... 086
Reposted by Rita ZhangDavid Fowler @davidfowl.com · 24/01/2025Did a talk this morning about my career and how to make an impact as an IC. Here's the last slide. 821535
Rita Zhang @ritazh.bsky.social · 19/12/2024🚀 Azure Upstream team is hiring in the US! Looking for Senior engineer to build cloud native OSS projects with #Kubernetes. 100% remote jobs.careers.microsoft.com/global/en/jo... DMs open! #opensource #hiringjobs.careers.microsoft.comSearch Jobs | Microsoft Careers 02522
Reposted by Rita Zhangsquillace @squillace.bsky.social · 11/12/2024If you are at kubecon india tomorrow, swing by the @microsoft.com both at 3 PM for some hot #webassembly action. We will help, we will scream, we will run on arm chips. #goFigure 1105
Reposted by Rita ZhangChris Aniszczyk @cra.dev · 12/12/2024#kubernetes running Black Friday at @ShopifyEng #kubecon #cloudnativecon India 084
Reposted by Rita ZhangMarcus Noble @averagemarcus.bsky.social · 11/12/2024Kuberentes v1.32 is being released this week and it's an exciting one! 🎉😁 I'm specifically excited about Mutating Admission Policies and pod level resource limits! lwkd.info/2024/20241210 #kubernetes #K8s 02411
Reposted by Rita ZhangBridget Kromhout @bridgetkromhout.bsky.social · 15/11/2024RBAC++ is a new area of exploration in SIG Auth (as presented by Anish Ramasekar with @ritazh.bsky.social and Jordan Liggitt). #KubeCon 2296