🎤 𝗦𝗹𝗶𝗱𝗲𝘀 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲! At #KubeCon North America 2025 in Atlanta, I had the pleasure of joining @ritazzhang, Jiaxin Shan, and Sergey Kanzhelev for our session: 𝘕𝘢𝘷𝘪𝘨𝘢𝘵𝘪𝘯𝘨 𝘵𝘩𝘦 𝘙𝘢𝘱𝘪𝘥 𝘌𝘷𝘰𝘭𝘶𝘵𝘪𝘰𝘯 𝘰𝘧 𝘓𝘢𝘳𝘨𝘦 𝘔𝘰𝘥𝘦𝘭 𝘐𝘯𝘧𝘦𝘳𝘦𝘯𝘤𝘦: 𝘞𝘩𝘦𝘳𝘦 𝘋𝘰𝘦𝘴 𝘒𝘶𝘣𝘦𝘳𝘯𝘦𝘵𝘦𝘴 𝘍𝘪𝘵? We covered: 1. The evolving landscape of AI-related Working Groups in the @kubernetesio community. 2. Emerging challenges from fast-moving inference architectures, heterogeneous hardware, distributed KV cache management, fault tolerance and recovery strategies for large-scale model inference. 3. Key initiatives from K8s WG Serving and relevant discussions in WG AI Conformance. 4. Solution showcases and reference architectures including LWS, DRA, AIBrix, @_llm_d_, KServe, Dynamo, and KAITO. 📑 Slides (link to recording will also be available soon): github.com/terrytangyuan/pub… The discussion highlighted how the Kubernetes ecosystem is quickly adapting to support 𝗻𝗲𝘅𝘁-𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗔𝗜 𝗮𝗻𝗱 𝗟𝗟𝗠 𝘄𝗼𝗿𝗸𝗹𝗼𝗮𝗱𝘀. This is only the beginning!

Back from #KubeCon and #CloudNativeCon North America 2025 in Atlanta! This has been the most fruitful @KubeCon_ of my career. It was an honor to return to the KubeCon keynote stage in front of more than 9,000 attendees! This time, Anjali Telang and I explored trust and identity in the AI era and how KServe connects seamlessly with security-focused technologies in the cloud-native ecosystem. Huge thanks to Josh Berkus and Laura Santamaria for their incredible speaker training, and to @sabre1041, @CJNuland, Jennifer Vargas, @SRickerd, and @stu for their unwavering support. 🔹Recording: youtu.be/Sw5uT4VkCHA?si=Gztg… In addition, thanks @cra and @CloudNativeFdn leadership for inviting me to the opening keynote stage to share a few words on the @kubernetesio AI Conformance Program, right after the amazing demo from @janet_kuo, along with my incredible co-leads @ritazzhang, @mfahlandt, and @janet_kuo. Thank you to everyone in the working group who's been contributing and driving this initiative forward. Special thanks to Laura Santamaria, Derek Carr, and Mrunal Patel for offering insights from both community and technical perspectives as well as @jwforres and @jtgreene for their support through our journey. 🔹Recording: youtu.be/cQvtT2vRhok?si=UiST… 🔹CNCF announcement: cncf.io/announcements/2025/1… I was fortunate to co-chair the Cloud Native & Kubernetes AI Day with @ahcorporto, Yuzhui Liu, and @RajasKakodkar, ensuring the event ran smoothly from start to finish. In this event, it was also great to pair up with Dan Sun, co-founder of KServe, to share insights on the project’s current state and future direction. 🔹Session: sched.co/28D4J 🔹CNCF announcement on KServe: cncf.io/blog/2025/11/11/kser… 🔹Red Hat announcement: redhat.com/en/blog/kserve-jo… It was equally exciting to discuss the state of model inference on Kubernetes with @ritazzhang, Jiaxin Shan, and Sergey Kanzhelev. 🔹Session: sched.co/27Nlv We also introduced the new CNCF TAG Workloads Foundation, along with Stephen Rust, @RajasKakodkar, and Alexander Scammon. Thank you @xu_paco and Marlow Warnicke for your contributions to the content. 🔹Session: sched.co/27NnE Last but not least, I want to thank the @RedHat leadership, John Graham, Sherard Griffin, Steven Huels, Taneem Ibrahim, Jennifer Albertson, and @kernelcdub, for their incredible support over the past two years and for giving me the opportunity to work so closely with the open source community. KubeCon 2025 was a milestone for AI, open source, and cloud-native innovation. I couldn’t be prouder to be part of it. Looking forward to another great year!