AI & ML

626 talks across 33 events, oldest first: 86 case studies where an organization reports its own experience, plus concept talks and tutorials.

Keywords: machine learning, ml, ai, llm, gpu, kubeflow, inference, training, model serving, kserve, ray, mlops, ai agents, generative ai (edit under categories: in wiki.yaml).

Over time

Year	Talks	Case studies
2016	1	0
2017	3	0
2018	36	4
2019	48	11
2020	29	6
2021	16	3
2022	14	2
2023	47	7
2024	133	12
2025	138	17
2026	161	24

Organizations with case studies

Intuit (3), Google (2), NVIDIA (2), Uber (2), Spotify (2), Seldon.io, Tesla, Pivotal, Gojek, Microsoft, Lyft, Baidu, Snapchat, Snap Inc, Day, Shell, Qihoo 360, IBM, Wolt, BentoML, CoreWeave, Alluxio, W. Lai, Volvo Cars, CERN, Bloomberg, Lucy, Andrea, Etienne, Tim, PepsiCo, Credit Karma, Alibaba, Murphy Chen, China, Massive, Netflix, CodeRabbit, Nutanix, Cisco

Talks by event

2016 · KubeCon + CloudNativeCon North America 2016 (Seattle)

• concept · State of the GPU(nion) by Rudi Chiarito, Clarifai

2017 · KubeCon + CloudNativeCon Europe 2017 (Berlin)

• concept · Building Distributed TensorFlow Using Both GPU and CPU on Kubernetes [I] - Zeyu Zheng

2017 · KubeCon + CloudNativeCon North America 2017 (Austin)

• concept · Democratizing Machine Learning on Kubernetes [I] - Joy Qiao & Lachlan Evenson, Microsoft
• concept · All You Need to Know to Build Your GPU Machine Learning Cloud [B] - Ye Lu, Qunar

2018 · KubeCon + CloudNativeCon China 2018 (Shanghai)

• case study · Kubeflow From the End User’s Perspective: The Good, The Bad, and The Ugly - Xin Zhang
• concept · CI/CD Pipelines and Machine Learning - Jeremy Lewi, Google
• concept · Kubernetes Love Machine Learning, Even on Private Cloud - Hui Luo, VMware
• concept · A Day in the Life of a Data Scientist. Conquer ML Lifecycle on Kubernetes - R. Zhang & B. Redmond
• concept · Serverless Kubernetes Boosts AI Business - Jian Huang, Huawei
• concept · A Year of Democratizing ML With Kubernetes & Kubeflow - David Aronchick & Fei Xue, Google
• concept · Deep Customized Kubernetes for Machine Learning in Tencent - Shengbo Song, Tencent
• concept · Operating Deep Learning Pipelines Anywhere Using Kubeflow - Jörg Schad & Gilbert Song, Mesosphere. Shows how to operate deep learning pipelines across environments using Kubeflow.
• concept · Benchmarking Machine Learning Workloads on Kubeflow - Xinyuan Huang, Cisco Systems, Inc. & Ce Gao. Benchmarks machine learning workloads running on Kubeflow.
• tutorial · Kubernetes CICD Hacks with MicroK8s and Kubeflow - Land Lu & Zhang Lei Mao, Canonical. Hands-on tips for CI/CD on Kubernetes using MicroK8s and Kubeflow.
• panel · Machine Learning on Kubernetes Birds of a Feather - David Aronchick. A birds-of-a-feather group discussion about running machine learning on Kubernetes.

2018 · KubeCon + CloudNativeCon Europe 2018 (Copenhagen)

• case study · Serving ML Models at Scale with Seldon and Kubeflow - Clive Cox, Seldon.io — Seldon.io
• concept · SAFE WG Intro – Jeyappragash J J, padme.io, & Ray Colline, Google (Any Skill Level)
• concept · Kubeflow Intro – Michał Jastrzębski & Ala Raddaoui, Intel (Any Skill Level)
• concept · Kubeflow Deep Dive – David Aronchick & Jeremy Lewi, Google (Intermediate Skill Level). Intermediate deep dive into Kubeflow for running machine learning workflows on Kubernetes.
• concept · Building a Go AI with Kubernetes and TensorFlow - Andrew Jackson & Josh Hoak, Google
• concept · Compliant Data Management and Machine Learning on Kubernetes - Daniel Whitenack, Pachyderm
• concept · Bringing Your Data Pipeline into The Machine Learning Era - Chris Gaun & Jörg Schad, Mesosphere
• concept · The Path to GPU as a Service in Kubernetes - Renaud Gaubert, NVIDIA (Intermediate Skill Level). Describes the path to offering GPUs as a service in Kubernetes.
• concept · Building ML Products With Kubeflow - Jeremy Lewi, Google & Stephan Fabel, Canonical
• concept · SAFE WG Deep Dive – Ray Colline, Google (Intermediate Skill Level)
• concept · Automating GPU Infrastructure for Kubernetes - Lucas Servén Marín, CoreOS
• concept · Conquering a Kubeflow Kubernetes Cluster with ksonnet, Ark, & Sonobuoy - Kris Nova & David Aronchick

2018 · KubeCon + CloudNativeCon North America 2018 (Seattle)

• case study · Lightning Talk: Cloud TPU? Don’t Mind If I Do - Nathan Murthy, Tesla — Tesla. Tesla's lightning talk on using Google Cloud TPUs for its own ML workloads.
• case study · Enterprise Machine Learning on K8s: Lessons Learned and the Road... - Timothy Chen & Tristan Zajonc
• concept · Machine Learning Model Serving and Pipeline Using KNative - Animesh Singh & Tommy Li, IBM
• concept · Scaling AI Inference Workloads with GPUs and Kubernetes - Renaud Gaubert & Ryan Olson, NVIDIA. Shows how to scale AI inference workloads using GPUs on Kubernetes.
• concept · Machine Learning as Code: and Kubernetes with Kubeflow - Jason " Jay" Smith & David Aronchick
• concept · Deep Dive: Kubeflow BoF - David Aronchick & Jeremy Lewi, Google
• concept · Eco-Friendly ML: How the Kubeflow Ecosystem Bootstrapped Itself - Peter MacKinnon, Red Hat
• concept · Natural Language Code Search for GitHub Using Kubeflow - Jeremy Lewi, Google & Hamel Husain, GitHub
• concept · Predictive Application Scaling with Prometheus and ML - Chris Dutra, Schireson
• concept · Machine Learning the Kubernetes Way - Ania Musial & Keith Laban, Bloomberg
• concept · How to Build Deep Learning Inference Through Knative Server... - Huamin Chen & Yehuda Sadeh-Weinraub. Shows how to build deep learning inference on Knative serverless infrastructure.
• concept · Nezha: A Kubernetes Native Big Data Accelerator For Machine Learning - Huamin Chen & Yuan Zhou
• tutorial · Tutorial: Kubeflow End-to-End: GitHub Issue Summarization - Michelle Casbon & Amy Unruh, Google

2019 · KubeCon + CloudNativeCon China 2019 (Shanghai)

• case study · How I Teach my Second Grade Kid what AI is and How this Relates to BI that Impact... Cupid Chan
• concept · Hyperparameter Tuning Using Kubeflow - Richard Liu, Google & Johnu George, Cisco Systems
• concept · Intro: Network Service Mesh (NSM) - Frederick Kautz, Doc.ai & Nikolay Nikolaev, VMware. Introduces Network Service Mesh and its approach to Kubernetes networking.
• concept · Co-Location of CPU and GPU Workloads with High Resource Efficiency - Penghao Cen & Jian He
• concept · Open Standards for Machine Learning Deployment - Animesh Singh & Hou Gang, IBM
• concept · Anomaly Detection for Cloud Native Storage - Seiya Takei & Xing Yang. Explores detecting anomalies in cloud native storage systems.
• concept · Introducing Kubeflow (w. Special Guests Tensorflow and Apache Spark) - Trevor Grant, IBM
• concept · Manage Multi-tenant ML Workloads Using Istio - Wencheng Lu & Limin Wang, Google
• concept · Build an Event Driven Machine Learning Pipeline on Kubernetes - Animesh Singh & Hou Gang, IBM
• concept · Minimizing GPU Cost for Your Deep Learning on Kubernetes - Kai Zhang & Yang Che, Alibaba
• concept · Multi-Cloud Machine Learning Data and Workflow with Kubernetes - Lei Xue, Momenta & Fei Xue, Google
• concept · The State of AI and Machine Learning Operations in 2019 - Alejandro Saucedo

2019 · KubeCon + CloudNativeCon Europe 2019 (Barcelona)

• case study · GPU Machine Learning From Laptop to Cloud - Mark Puddick, Pivotal — Pivotal
• case study · Accelerating the Journey of an AI Algorithm to Production with OpenFaaS - Joost Noppen & Alex Ellis
• case study · Moving People and Products with Machine Learning on Kubeflow - Jeremy Lewi, Google & Willem Pienaar — Google, Gojek. Google and Gojek (Willem Pienaar's team) show how they use Kubeflow to run machine learning for moving people and products.
• case study · Managing Machine Learning in Production with Kubeflow and DevOps - David Aronchick, Microsoft — Microsoft
• case study · Production GPU Cluster with K8s for AI and DL Workloads - Madhukar Korupolu, NVIDIA — NVIDIA. NVIDIA describes running production GPU clusters on Kubernetes for AI and deep learning workloads.
• concept · Intro: Network Service Mesh (NSM) - Frederick Kautz, Doc.ai & Ed Warnicke, Cisco
• concept · Building Cross-Cloud ML Pipelines with Kubeflow with Spark & Tensorflow - Holden Karau
• concept · Towards Kubeflow 1.0, Bringing a Cloud Native Platform For ML to Kubernetes - David Aronchick. Outlines the road to Kubeflow 1.0 as a cloud native ML platform on Kubernetes.
• concept · Deep Dive: Network Service Mesh (NSM) - Nikolay Nikolaev, VMware & Frederick Kautz, Doc.ai. Deep dive into the architecture of Network Service Mesh.
• concept · Economics and Best Practices of Running AI/ML Workloads on Kubernetes - Maulin Patel
• concept · A Tale of Two Worlds: Canary-Testing for Both ML Models and Microservices - Jörg Schad
• concept · GPU Sharing for Machine Learning Workload on Kubernetes - Henry Zhang & Yang Yu, VMware
• tutorial · Tutorial: Introduction to Kubeflow Pipelines - Michelle Casbon, Dan Sanche, Dan Anghel
• panel · Panel Discussion: Democratizing HPC & AI: Startups Scale Up with Cloud Native
• other · KubeFlow BoF: David Aronchick, Microsoft & Yaron Haviv, Iguazio. Birds-of-a-feather discussion on Kubeflow led by Microsoft and Iguazio representatives.

2019 · KubeCon + CloudNativeCon North America 2019 (San Diego)

• case study · Measuring and Optimizing Kubeflow Clusters at Lyft - Konstantin Gizdarski & Richard Liu — Lyft
• case study · Towards Continuous Computer Vision Model Improvement with Kubeflow - Derek Hao Hu & Yanjia Li. Describes using Kubeflow to build a continuous improvement pipeline for computer vision models.
• case study · Kubernetizing Big Data and ML Workloads at Uber - Mayank Bansal & Min Cai, Uber — Uber
• case study · Building and Managing a Centralized Kubeflow Platform at Spotify - Keshi Dai & Ryan Clough, Spotify — Spotify
• case study · Improving Performance of Deep Learning Workloads With Volcano - Ti Zhou, Baidu Inc — Baidu. Baidu shows how Volcano improved performance of its deep learning workloads.
• concept · Lightning Talk: Sharing a GPU Among Multiple Containers - Patrick McQuighan, Algorithmia
• concept · Lightning Talk: Kuber-What-Es?! Misadventures in Building UIs for K8s-Based ML... Alexandra Johnson
• concept · KubeFlow’s Serverless Component: 10x Faster, a 1/10 of the Effort - Orit Nissan-Messing, Iguazio
• concept · Enabling Kubeflow with Enterprise-Grade Auth for On-Prem... Yannis Zarkadas & Krishna Durai
• concept · Introducing KFServing: Serverless Model Serving on Kubernetes - Ellis Bigelow & Dan Sun
• concept · How Ancestry Got Kubernetes to Run 2x Better Per Dollar Using AI - Darek Gajewski, Ancestry
• concept · Advanced Model Inferencing Leveraging KNative, Istio & Kubeflow Serving - Animesh Singh & Clive Cox
• concept · Kubeflow: Multi-Tenant, Self-Serve, Accelerated Platform for Practitioners- Kam Kasravi & Kunming Qu
• concept · GPU as a Service Over K8s: Drive Productivity and Increase Utilization - Yaron Haviv, Iguazio
• concept · Building a Medical AI with Kubernetes and Kubeflow - Jeremie Vallee, Babylon Health
• concept · Supercharge Kubeflow Performance on GPU Clusters - Meenakshi Kaushik & Neelima Mukiri, Cisco
• concept · Realizing End to End Reproducible Machine Learning on Kubernetes - Suneeta Mall, Nearmap
• concept · KubeVirt Deep Dive: Virtualized GPU Workloads on KubeVirt - David Vossel & Vishesh Tanksale
• concept · Flyte: Cloud Native Machine Learning & Data Processing Platform - Ketan Umare & Haytham AbuelFutuh
• tutorial · Tutorial: From Notebook to Kubeflow Pipel... Michelle Casbon, Stefano Fioravanzo & Ilias Katsakioris
• panel · Panel: Enterprise-grade, On-prem Kubeflow in the Financial Sector

2020 · KubeCon + CloudNativeCon Europe 2020 - Virtual

• case study · Monitoring GPUs at Scale for AI/ML and HPC Clusters - Bharti L Agrawal, NVIDIA — NVIDIA
• concept · Enabling Multi-user Machine Learning Workflows for Kubeflow Pipelines - Yannis Zarkadas & Yuan Gong
• concept · Taming Data/State Challenges for ML Applications and Kubeflow - Skyler Thomas, Hewlett Packard
• concept · Sponsor Demo: SUSE - Power AI Using Kubeflow / Deliver Applications Faster using Kubernetes
• concept · Is There a Place For Distributed Storage For AI/ML on Kubernetes? - Diane Feddema & Kyle Bader. Discusses the role of distributed storage for AI/ML workloads on Kubernetes.
• concept · Episode IV: A New Network Service Mesh - Frederick Kautz, Doc.ai & Nikolay Nikolaev, VMware
• concept · Owned By Statistics: How Kubeflow & MLOps Can Help Secure Your ML Workloads - David Aronchick. Shows how Kubeflow and MLOps practices can help secure ML workloads.
• concept · Is Sharing GPU to Multiple Containers Feasible? - Samed Güner, SAP
• concept · Elephant on Wheels: Petabyte-scale AI @ LinkedIn - Cong Gu & Abin Shahab, LinkedIn
• concept · Expanding Serverless to Scale-out Kubeflow Pipelines - Yaron Haviv, Iguazio
• concept · Kubeflow 1.0 Update by a Kubeflow Community Product Manager - Josh Bottum, Arrikto. Community update on the Kubeflow 1.0 release and what comes next.
• concept · How to Use Kubernetes to Build a Data Lake for AI Workloads - Peter MacKinnon & Uday Boppana. Shows how to build a data lake for AI workloads on Kubernetes.
• concept · Effective Kubernetes Onboarding - Kathleen Juell, DigitalOcean. Offers guidance on how to onboard newcomers to Kubernetes effectively.
• tutorial · Tutorial: From Notebook to Kubeflow Pipelines with HP Tuni... Stefano Fioravanzo & Ilias Katsakioris
• tutorial · Tutorial: KubeEdge Hands on Workshop -- Build Your Edge AI App on Real Ed... Zefeng Wang & Zhang Jie
• other · Sponsor Demo: AWS - TorchElastic Controller for Kubernetes. AWS sponsor demo of the TorchElastic controller for Kubernetes.

2020 · KubeCon + CloudNativeCon North America 2020 - Virtual

• case study · Analyzing Operational Data at Scale Using ML at Intuit - Amit Kalamkar & Vigith Maurice, Intuit — Intuit
• case study · MLOps at Snapchat: Continuous Machine Learning with Kubeflow & Spinnaker - Kevin Dela Rosa, Snap Inc — Snapchat, Snap Inc
• case study · Cloud Native Machine Learning Systems at Day Two and Beyond - Sophie Watson & William Benton — Day
• case study · Machine Learning on Kubernetes at Shell: A Kubeflow Journey - Alex Iankoulski & Vangelis Koukis — Shell
• case study · High Performance Networking for Distributed DL Training in Production K8s - Nivedita Viswanath
• concept · Scaling to Millions of ML Models to Solve the Problems of SRE and Security - Sandeep Pombra. Describes scaling to millions of ML models to address SRE and security problems.
• concept · Kubernetes Operators: Safety First Through Model Checkers - Neven Miculinic, grid.ai
• concept · Serverless for ML Inference on Kubernetes: Panacea or Folly? - Manasi Vartak, Verta Inc
• concept · Building a Cloud Native Feature Store with Feast on Kubeflow - Willem Pienaar & Oleksii Moskalenko
• concept · Accelerate and Autoscale Deep Learning Inference on GPUs with KFServing - Dan Sun
• concept · Owned by Statistics: Using Kubeflow to Defend vs Attacks on Your ML Models - David Aronchick
• tutorial · Tutorial: From Notebook to Kubeflow Pipelines to KFServing: the Data Science... - Karl Weinmeister
• panel · Panel: Introduction to the Container Orchestrated Device (COD) Working Group - Renaud Gaubert. Introduction to the Container Orchestrated Device working group and its goals for device support in orchestrators.

2021 · KubeCon + CloudNativeCon + Open Source Summit China 2021

• case study · DGL Operator: Distributed Graph Neural Network Training with DGL and K8s - Xiaoyu Zhai, Qihoo 360 — Qihoo 360. Qihoo 360 presents a DGL Operator for distributed graph neural network training on Kubernetes.
• concept · Vivo's AI Computing Platform on Kubernetes - Ziyang Wu, Vivo
• concept · ML training acceleration with heterogeneous resources in Bytedance- Deliang Fan & Tao Xin, ByteDance
• concept · Deep Dive: CRI- RM Based CPU and NUMA Affinity to Achieve AI Task Accele... Dekui Wang & Jerry Wang
• concept · Beyond CUDA: GPU Accelerated Computing on Cross-Vendor Graphics Cards with Vulk... Alejandro Saucedo
• concept · Accelerate Federated Learning Model Deployment with KServe (KFServing) - Fangchi Wang & Jiahao Chen

2021 · KubeCon + CloudNativeCon Europe 2021

• concept · Building and Managing a Centralized ML Platform with Kubeflow at... Ricardo Rocha & Dejan Golubovic
• concept · Automated Machine Learning Performance Evaluation - Alejandro Saucedo
• concept · Optimizing Knowledge Distillation Training With Volcano - Ti Zhou, Baidu & William Wang, Huawei
• concept · Efficient Model Exploring and Continuous Delivery With Polyaxon + Kubeflow - Shotaro Kohama
• concept · Building MLOps POCs and Sandbox Environments Using k3s and Argo - Sergio Mendez

2021 · KubeCon + CloudNativeCon North America 2021

• case study · Scaling Kubeflow for Multi-tenancy at Spotify - Keshi Dai & Jonathan Jin, Spotify — Spotify
• case study · Serving Machine Learning Models at Scale Using KServing - Animesh Singh, IBM — IBM
• concept · Life is not fair, but your ML pipeline can be! - Meenakshi Kaushik & Neelima Mukiri, Cisco
• concept · AIoT Ops - Using Kubernetes and ML Ops to Build Edge ML Applications - Asheesh Goja, Cisco
• concept · Scaling Machine Learning Workflows to Big Data with Fugue - Kevin Kho, Prefect & Han Wang, Lyft

2022 · KubeCon + CloudNativeCon Europe 2022

• case study · Accelerating High-Performance Machine Learning at Scale i... Alejandro Saucedo & Elena Neroslavskaya
• case study · Scaling Open Source ML: How Wolt Uses K8s To Deliver Great Food to Mill... Stephen Batifol & Ed Shee — Wolt. Wolt explains how it uses Kubernetes and open source tools to scale ML for food delivery.
• concept · The Future Of Reproducible Research: Powered By Kubeflow - Trevor Grant
• concept · Jet Energy Corrections with GNN Regression using Kubeflow @ CERN - Daniel Holmberg & Dejan Golubovic
• concept · Tower of Babel: Making Apache Spark, Kubeflow, and Kubernetes Play Nice - Holden Karau, Netflix. Explains how to make Spark, Kubeflow and Kubernetes work together smoothly.
• concept · How Cookpad Leverages Triton Inference Server To Boost Their Model S... Jose Navarro & Prayana Galih
• concept · Improving GPU Utilization using Kubernetes - Maulin Patel & Pradeep Venkatachalam, Google

2022 · KubeCon + CloudNativeCon North America 2022

• concept · Kubernetes On the Edge With K3s For a Smart Metering Use Case - Harry Lee, Melio AI
• concept · Kubernetes For GPU Powered Machine Learning Workloads In... - Camille Rodriguez & John-Paul Robinson
• concept · Machine Learning Using Various GPU Technology With Kubeflow. - Jihye Choi, SAMSUNG SDS
• concept · Computational Fluid Dynamics (CFD) Analysis With Kubernetes, Kubeflow, And OpenFOAM - Erik Jacobs
• concept · MetaOps: Metadata Operations For End-To-End Data & Machine Learning Platforms - Alejandro Saucedo
• concept · Observability In ArgoCD/Rollouts Using Streaming ML For Reducing MTTR - Vigith Maurice & A Kalamkar. Shows using streaming ML on ArgoCD/Rollouts observability data to reduce MTTR.
• concept · Training AI To Code Using the Largest Code Dataset - Tommy Li & Animesh Singh, IBM

2023 · KubeCon + CloudNativeCon + Open Source Summit China 2023

• case study · From Zero to Infinity: How AI-Powered Hedge Fund Build Cloud-Native AI Platfo... Yang Che & Zhiyi Li
• case study · Accelerating AI Application: NAVER's Journey from Model to Application - Eric Liu, BentoML — BentoML
• concept · Develop, Build & Deploy Lightweight AI Services with WebAssembly - Kinfey Lo, Vivian Hu, Jianbai Ye
• concept · Practice of Building AI Training Cluster Based on Kubernetes+RoCEv2 - Wang DeKui & Wang Chao IEI
• concept · Boost ML on Heterogeneous AI Accelerator with Ray on K8s - Tiejun Chen, VMware
• concept · How to Accelerate Model Training and Eliminate the I/O bottleneck for the Cloud - Rui Su, Juicedata
• concept · Dragonfly: Intro, Updates and AI Model Distribution in the Practice of... - Wenbo Qi & Zekun Liu
• concept · Run Your AI Workloads and Microservices on Kubernetes More Easily and Efficiently... - William Wang
• concept · Lightning Talk: Sailing Kubernetes Operation with AI Power - Peter Pan, Daocloud
• concept · Sailing Ray Workloads with KubeRay and Kueue in Kubernetes - Jason Hu, Volcano Engine & Kante Yin
• concept · Toward Seamless Model Compilation Integration - Hongyu Zhu, ByteDance. Discusses integrating model compilation seamlessly into ML serving workflows.
• concept · LLM as a Robotic Brain: Cloud-Driven Robot Action Sequences Generated by Large... - Sitong Mao. Shows how large language models running in the cloud can generate robot action sequences.
• concept · Consolidation in Benchmarking, Optimization, and Ecosystem Collaboration for AI ASICs - Minghui Yu
• concept · Shuhe Accelerates AI Model Service Deployment with Knative - Peng Li, Alibaba Cloud & Wenzhe Wei
• concept · Cloud Native Storage CubeFS, Empowering AI Acceleration - Hu Yao, OPPO
• concept · WebAssembly-Based FaaS Framework with Distributed Machine Learning... - Wilson Wang & Michael Yuan. Presents a WebAssembly-based FaaS framework supporting distributed machine learning.

2023 · KubeCon + CloudNativeCon Europe 2023

• concept · Efficient Access to Shared GPU Resources: Mechanisms and Use Cases - Diogo Guerra & Diana Gaponcic
• concept · The State and Future of Cloud-Native Model Serving - Dan Sun, Bloomberg & Theofilos Papapanagiotou. Overview of the current state and future direction of cloud-native model serving, centered on KServe.
• concept · Hardening Kubeflow Security for Enterprise Environments - Julius Kohout & Diana Dimitrova Atanasova
• concept · Enabling HPC & ML Workloads with the Latest Kubernetes Job Features- Michał Woźniak & Vanessa Sochat
• concept · How to Leverage Volcano to Improve the Resource Utilization of AI Pharmaceuticals... - William Wang
• concept · Building on-Premises MLOps for ISS Columbus Ground Operations - Samo Turk & Christian Geier

2023 · KubeCon + CloudNativeCon NA 2023

• case study · Reducing AI Job Cold Start Time from 15 Mins to 1 Min - Tao He, Google — Google
• case study · How the Record-Breaking, Cloud Native AI Supercomputer Was Built - Peter Salanki, CoreWeave — CoreWeave. CoreWeave describes how it built a record-breaking cloud native AI supercomputer on Kubernetes.
• case study · Mastering LLM Delivery in Private Clouds: A Journey to Seamless Dep... Autumn Moulder & Marwan Ahmed
• case study · The Journey Along the Way to Data-locality on Cloud for AI/ML - Shawn Sun & Lu Qiu, Alluxio — Alluxio
• case study · Real-World Knative: Success Stories from Production Environments.... Four guest speakers describe how their organizations use Knative in production.
• concept · Dragonfly V2.1.0 - Intro, Updates and Practice in AI Model Distribution - Wenbo Qi, Ant Group
• concept · Unlocking the Full Potential of GPUs for AI Workloads on Kubernetes - Kevin Klues, NVIDIA. Explains how to get more from GPUs for AI workloads on Kubernetes, including dynamic resource allocation.
• concept · Accelerate Your GenAI Model Inference with Ray and Kubernetes - Richard Liu, Google Cloud
• concept · The Best Practice of Machine Learning Platform Storage Based on CubeFS - Leon Chang, OPPO
• concept · Supercharge Your AI Platform with KubeRay: Ray + Kubernetes - Archit Kulkarni & Winston Chiang
• concept · The Hidden Heroes Behind AI: Making Sense of GPUs and TPUs in K8s - David Porter & Evan Lezar
• concept · Maximizing GPU Utilization in Kubernetes with Virtual Kubelets - Goutam Verma & Dean Troyer
• concept · Kube of Thoughts – Scaling Generative AI Models with Kubernetes and Inference Decisi... Asheesh Goja
• concept · How NATS Is Designed to Deliver AI Workloads at the Edge - Byron Ruth & Jeremy Saenz, Synadia. Explains how NATS is designed to deliver AI workloads at the edge.
• concept · The Complexity on Scaling ML Pipelines on Kubernetes Using Tekton - Tommy Li, IBM
• concept · Environmentally Sustainable AI via Power-Aware Batch Scheduling - Atanas Atanasov & Daniel Wilson. Presents power-aware batch scheduling as a way to reduce the environmental impact of AI workloads.
• concept · Achieving Real-Time Generative AI During Gameplay for Games Running on Kubernetes - Ishan Sharma
• concept · K8sGPT: Balancing AI's Productivity Boost with Ethical Considerations in Cloud-Native - Alex Jones
• concept · An Offer You Can't Refuse: Discovering Chicago Film Sets with MLOps in... Annie Talvasto & Adi Polak
• concept · Beyond Prototypes: Production-Ready ML Systems with Metaflow and Argo Pro... Savin Goyal & Yuan Tang
• concept · Efficient Edge Computing: Unleashing the Potential of AI/ML... Ricardo Noriega De Soto & Alex Mevec. Explores how to run AI/ML workloads efficiently at the edge.
• concept · The Cloud-Native Workloads Journey Through the CNCF Tag-Runtime - Ricardo Aravena, TruEra. Overview of CNCF TAG Runtime activities and working groups and how to get involved.
• concept · On-Demand Systems and Scaled Training Using the JobSet API - Abdullah Gharaibeh & Vanessa Sochat
• concept · Lightning Talk: Generative AI for Platform Engineering - Jeremy Lewi, Sailplane AI. Lightning talk on applying generative AI to platform engineering.
• keynote · Grifts Ahoy! Bracing for the AI Tide - Shane Lawrence, Shopify. Shopify's Shane Lawrence offers a cautionary perspective on preparing for the AI wave.

2024 · KubeCon + CloudNativeCon + Open Source Summit + AI_dev China 2024

• concept · Boosting LLM Development and Training Efficiency: Automated Parallelization with Min... - Yiren Xing
• concept · Java Me Smarter: Unleashing AI Power with Quarkus | Java让我更聪明：用Quarkus释放人工智能的力量 - Daniel Oh, Red Hat
• concept · CubeFS Boosts Efficiency of AI Production | CubeFS提高了AI生产的效率 - Chi He, OPPO
• concept · Detecting and Overcoming GPU Failures During ML... - Ganeshkumar Ashokavardhanan & Sarah Belghiti. Covers detecting and recovering from GPU failures during ML workloads.
• concept · Unveiling the Future: Nurturing Openness in AI Development | 揭示未来：培育人工智能开放性发展 - Anni Lai & Mer Joyce
• concept · Write Once Run Anywhere, but for GPUs | GPU 时代的“一次编写，到处运行” - Michael Yuan, Second State
• concept · LLM's Anywhere: Browser Deployment with Wasm & WebGPU - Joinal Ahmed & Nikhil Rana. Shows how to run large language models directly in the browser using WebAssembly and WebGPU.
• concept · Breaking Boundaries: TACC as an Unified Cloud-Native Infra for AI + HPC - Peter Pan & Kaiqiang Xu
• concept · Model Service Mesh: A New Paradigm for Large-Scale AI Model Servic...- Xi Ning Wang & Huailong Zhang
• concept · Constructing the 10x Efficiency of Cloud-Native AI Infrastructure - Peter Pan, DaoCloud & 秋萍 戴
• concept · New Advances for Cross-Platform AI Applications in Docker | Docker中跨平台AI应用程序的新进展 - Michael Yuan
• concept · Optimize LLM Workflows with Smart Infrastructure Enhanced by Volcano - Xin Li & Xuzheng Chang. Shows how Volcano helps optimize LLM workflows through smarter scheduling infrastructure.
• concept · Unlocking LLM Performance with EBPF: Optimizing Training and Inference Pipelines - Yang Xiang
• concept · JuiceFS CSI in Multi-Thousand Node Kubernetes Clusters for LLM Pre-Training - Weiwei Zhu
• concept · Navigating the Ethical Horizon: Pioneering Responsible AI with the Generative AI Commons - Anni Lai
• concept · Effortless Scalability: Orchestrating Large Language Model Inference...- Joinal Ahmed & Nirav Kumar
• concept · dora-rs: Dataflow Oriented Robotic AI framework | dora-rs：面向数据流的机器人AI框架 - Xavier Tao, 1ms.ai
• concept · VeScale: A PyTorch Native LLM Training Framework | veScale：一个PyTorch原生LLM训练框架 - Hongyu Zhu. Presents veScale, a PyTorch-native framework for training LLMs.
• concept · Accelerating Serverless AI Large Model Inference with Functionalized... - Yiming Li & Chenglong Wang
• concept · Leveraging Wasm for Portable AI Inference Across GPUs, CPUs, OS & Cloud...- Miley Fu & Hung-Ying Tai
• concept · Leverage Topology Modeling and Topology-Aware Scheduling to Accelerate LLM Training - William Wang
• concept · How Fast Can Your Model Composition Run in Serverless Inference? - Fog Dong, BentoML & Wenbo Qi
• concept · Connecting the Dots: Towards a Unified Multi-Cluster AI/ML Experience - Qing Hao, Red Hat & Chen Yu
• concept · Boundaryless Computing: Optimizing LLM Performance, Cost, and Efficiency in...- Jian Zhu & Kai Zhang
• concept · AI Inference Performance Acceleration: Methods, Tools, and Deployment Workflows - Yifei Zhang & 磊 钱
• concept · Unlocking Heterogeneous AI Infrastructure K8s Cluster: Leveraging the...- Xiao Zhang & Mengxuan Li
• concept · Simplify AI Infrastructure with Kubernetes Operators - Ganeshkumar Ashokavardhanan & Tariq Ibrahim
• concept · Self-Hosted LLM Agent on Your Own Laptop or Edge Device | 在自己的笔记本电脑或边缘设备上自托管LLM Agent - Michael Yuan
• concept · Is Your GPU Really Working Efficiently in the Data Center? N Ways to... - Xiao Zhang & Wu Ying Jun
• concept · Ethics in the Cloud: Safeguarding Responsible AI Development in Asia - Quiana Berry, Red Hat. Discusses ethical considerations and safeguards for responsible AI development in Asia.
• concept · Tackling Operational Time-to-Market Decelerators in AI/ML Projects - Adrian Matei & Andreea Munteanu
• concept · Kubespray Unleashed: Navigating Bare Metal Services in Kubernetes for LLM... - Kay Yan & Alan Leung
• concept · Lightning Talk: Running Native WebAssembly AI Applications Everywhere - Tiejun Chen, VMware
• concept · Lightning Talk: How Prometheus AI Agent Helps Build Interactive Monitoring? - Zhihao Liu, Quwan
• concept · KubeCon + CloudNativeCon + OSS + AI Dev China 2024 Highlight Reel

2024 · KubeCon + CloudNativeCon Europe 2024

• case study · Precision Matters: Scheduling GPU Workloads on Kubernetes - Amit Kumar & Gaurav Kumar, Uber — Uber. Uber describes how it schedules GPU workloads on Kubernetes with attention to precision and resource fit.
• case study · From Insanity to Ingenuity: Seven Practical Tips for Navigating the AI Storm in DBaaS Evolution
• case study · From Bash Scripts to Kubeflow and GitOps: Our Journey to Operationalizing ML at Scale
• concept · Distributed AI: Using NATS.Io to Seamlessly Connect AI Applications... Tomasz Pietrek & Jeremy Saenz
• concept · Maximizing GPU Utilization Over Multi-Cluster: Challenges and Solutions for Cloud-Native AI Platform
• concept · Kubernetes MLSec: Securing AI in Space - Francesco Beltramini & James Callaghan, ControlPlane
• concept · Mastering GPU Management in Kubernetes Using the Operator Pattern- Shiva Krishna Merla & Kevin Klues
• concept · Increasing GPU Utilisation on K8s Clusters Dedicated for AI/ML Workloads
• concept · Production-Ready AI Platform on Kubernetes - Yuan Tang, Red Hat
• concept · Confidential Containers for GPU Compute: Incorporating LLMs in a Lift-and-Shift Strategy for AI
• concept · Unleashing the Power of DRA (Dynamic Resource Allocation) for Just-in-Time GPU Slicing
• concept · Unlocking the TAG-Runtime Magic: Where Cloud-Native, Workloads, and AI Join Forces!. Overview of TAG-Runtime's work on cloud native workloads and AI.
• concept · Fortifying AI Security in Kubernetes with Confidential Containers (CoCo)
• concept · Intelligent Observability: The Foundation for Operating Smarter in the Age of AI - Alolita Sharma. Explains intelligent observability as a foundation for operating smarter in the age of AI.
• concept · Accelerators(FPGA/GPU) Chaining to Efficiently Handle Large AI/ML Workloads in K8s
• concept · OCI as a Standard for ML Artifact Storage and Retrieval - Peyman Norouzi & Eric Koepfle, Bloomberg
• concept · AI, Edge, and Storage Walk Into a Mongolian Mine - Reza Jelveh, SoftSage Solutions OU
• concept · Cloud-Native LLM Deployments Made Easy Using LangChain - Ezequiel Lanza & Arun Gupta, Intel
• concept · Playing Defense: The Reactive Cloud Native Security Battle - Ayse Kaya, Slim.AI
• concept · Strategies for Efficient LLM Deployments in Any Cluster -Angel M De Miguel Meana & Francisco Cabrera
• concept · Breaking the Rules of Operator Development for AI at the Far Edge
• concept · How to Choose the Best Kubernetes AI Edge Deployment Patterns for Your Use Case
• concept · Gen AI at the Edge: How Cloud Native Technologies Enable the Next Wave of Intelligent Applications
• concept · Navigating the Processing Unit Landscape in Kubernetes for AI Use Cases. Surveys the processing unit options (GPUs, TPUs and others) in Kubernetes for AI use cases.
• concept · Advanced Resource Management for Running AI/ML Workloads with Kueue - Michał Woźniak, Yuki Iwai. Covers advanced resource management features in Kueue for running AI/ML workloads.
• concept · AI-Assisted Runbooks - Instigating Precision and Efficiency in Kubernetes Operations. Shows how AI-assisted runbooks can make Kubernetes operations more precise and efficient.
• concept · Dragonfly V2.2.0 - Intro, Updates, Model Distribution in AI Inference and Data Distribution in Serve
• concept · The State of K8sGPT: Your Troubleshooting Companion | Project Lightning Talk. Project update on K8sGPT, an AI-based Kubernetes troubleshooting tool.
• concept · WasmEdge, portable and lightweight runtime for AI/LLM workloads | Project Lightning Talk
• concept · Lightning Talk: AI and Kubernetes: Achieving Together in the Next Decade - Steven Zou, VMware
• concept · Sharing Is Caring: GPU Sharing and CDI in Device Plugins - Christopher Desiniotis & David Porter. Covers GPU sharing and the Container Device Interface in Kubernetes device plugins.
• tutorial · KubeDDR! a Dance of Predictive Scoring with MLOps, Step by Step - Leigh Capili & Annie Talvasto. A playful step-by-step MLOps demo building a predictive scoring game on Kubernetes.
• tutorial · How to Deploy an AI-Optimized K8s Cluster with Kubespray - Kay Yan & Mohamed Zaian. Demonstrates deploying an AI-optimized Kubernetes cluster with Kubespray.
• tutorial · Tutorial: Cloud Native Sustainable LLM Inference in Action

2024 · KubeCon + CloudNativeCon India 2024

• case study · Scaling Private LLM Model Services with Kserve and Modelcar OCI: A Real-World... - Mayuresh Krishna
• concept · Wasm Powered Open source LLMs and AI Agent | Project Lightning Talk. Lightning talk on running open source LLMs and AI agents with Wasm.
• concept · Guardians of the MLOps Galaxy: Simplifying Deployments with Buil...- Suman Chakraborty & Aditya Soni
• concept · Optimizing 5G Networks: Deploying AI/ML Workloads with the AIMLFW of O-RAN SC - Subhash Kumar Singh
• concept · Streamlining Machine Learning Operations with GitOps - Kunal Kushwaha, Civo
• concept · GenAI Recipes For Cloud Native Deployment - Arun Gupta, Intel & Kaushal Desai, Infosys. Recipes for deploying GenAI workloads in a cloud native way.
• concept · Lightning Talk: Enhancing Hyperparameter Optimization with Advanced Parameter... - Shashank Mittal. Lightning talk on enhancing hyperparameter optimization with advanced parameter techniques.
• concept · Search/Vector DBs as Microservices: Pros and Cons - Radu Gheorghe, Vespa.ai
• concept · Unleashing Generative AI with Open Data Hub - Ritesh Shah, Red Hat
• concept · End to End LLMOps with Kubeflow - J. George, G. Prabhu, A. Nagar & A. Raimule, K. Durai
• concept · Scalable ML Inferencing Pipeline Using K8s - Smitha Jayaram & Vinod Eswaraprasad, NVIDIA. Presents an architecture for building scalable ML inferencing pipelines on Kubernetes using NVIDIA tooling.
• concept · Azimuth - AstraZeneca’s Cloud Native Machine Learning Platform - Nithin R, AstraZeneca
• concept · From CPU to GPU: Progressive Delivery for Complex ML Deployments - Sumit Jain & Divyansh Saxena. Covers progressive delivery strategies for complex ML deployments moving from CPU to GPU.
• concept · Using vectordb for Data on S3 Bucket - Jiffin Tony Thottan, IBM. Shows how to use a vector database with data stored in S3 buckets.
• tutorial · Tutorial: An Accelerated Introduction to AI Model Deployment with...- Sreeram Venkitesh & Emily Chen
• tutorial · Introduction to Distributed ML Workloads with Ray on Kubernetes - Kavitha Gowda, Google

2024 · KubeCon + CloudNativeCon NA 2024 - Salt Lake City

• case study · From Chaos to Harmony, Transforming ML Engineering: A Kubernetes Adoption Journey - P.N. Kejser
• case study · From Silicon to Service: Ensuring Confidentiality in Serverless GPU Cloud Functions - Zvonko Kaiser
• case study · Towards Zero Change Incidents: Intuit's Strategy for Implementing AI... A. Basu, S. Balasubramanian — Intuit. Intuit describes its strategy for using AI to move toward zero change-caused incidents.
• case study · Production AI at Scale: Cloudera’s Journey in Building a Robust Inference Pl... Z. Thanga, P. Ableda
• case study · Operationalizing High-Performance GPU Clusters in Kubernetes: Lessons Learned fr... W. Gleich, W. Wu
• case study · Discover CNCF TAG Runtime: From AI, WASM, OS, Edge to Workloads in the Heart of Salt Lake City
• case study · Bloomberg's Journey to Manage a Multi-Cluster Training Application with Karmada - Y. Zhang, W. Lai — W. Lai
• case study · From Vectors to Pods: Integrating AI with Cloud Native - Panel
• concept · Distributed Cache Empowers AI/ML Workloads on Kubernetes Cluster - Yuichiro Ueno & Toru Komatsu
• concept · Engaging the KServe Community, The Impact of Integrating a Solutions with Standardized CNCF Projects
• concept · Elevating Kubeflow Spark Operator's Future: Best Practices and Enhancements- Vara Bonthu, Chaoran Yu. Covers best practices and planned enhancements for the Kubeflow Spark Operator.
• concept · Navigating Failures in Pods with Devices: Challenges and Solutions - Sergey Kanzhelev & Mrunal Patel. Discusses challenges and solutions for handling failures in pods that use devices.
• concept · Observability TAG Round-up and What’s New for AI Observability - Alolita Sharma & Chris Larsen
• concept · Building Resilience for Large-Scale AI Training: GPU Management, Fa... G. Ashokavardhanan, A. Eldeib
• concept · Optimizing Load Balancing and Autoscaling for Large Language Model (LLM) Inference on Kub... D. Gray
• concept · Platform Performance Optimization for AI - a Resource Management Perspective- A. Kervinen, D. Narang
• concept · Optimizing LLM Performance in Kubernetes with OpenTelemetry - Ashok Chandrasekar & Liudmila Molkova. Shows how to use OpenTelemetry to observe and optimize LLM performance on Kubernetes.
• concept · A Tale of 2 Drivers: GPU Configuration on the Fly Using DRA- Alay Patel & Varun Ramachandra Sekar US
• concept · AI and ML: Let’s Talk About the Boring (yet Critical!) Operational Side- Rob Koch & Milad Vafaeifard. Looks at the operational side of running AI and ML workloads.
• concept · Advanced Model Serving Techniques with Ray on Kubernetes - Andrew Sy Kim & Kai-Hsun Chen
• concept · Tackling GPU Shortages and High Costs by Harnessing Hybrid Kubernetes Clusters - X. Dong, A. Pucher
• concept · Load-Aware GPU Fractioning for LLM Inference on Kubernetes - Olivier Tardieu & Yue Zhu, IBM
• concept · Democratizing AI Model Training on Kubernetes with Kubeflow TrainJob and... A. Velichkevich, Y. Iwai
• concept · Which GPU Sharing Strategy Is Right for You? A Comprehensive Benchmark Study Us... K. Klues, Y. Chen
• concept · Better Together! GPU, TPU and NIC Topological Alignment with DRA - John Belamaric & Patrick Ohly. Explains how DRA aligns GPU, TPU and NIC topology for better workload performance.
• concept · Building Massive-Scale Generative AI Services with Kubernetes and Open Source - John McBride
• concept · Best Practices for Deploying LLM Inference, RAG and Fine Tuning Pipelines... M. Kaushik, S.K. Merla
• concept · The State of Kubernetes Optimization and the Role of AI - Panel
• concept · Open Cluster Management: Scheduling AI Workload Among Multiple Clusters | Project Lightning Talk
• concept · CNCF Runtime TAG: CNCF Runtime TAG and the Cloud Native Runtime Landspace: AI, WASM, OS, Edge, Wo...
• concept · CRI-O: First Class AI Model Teleportation - OCI Volume Mounts in CRI-O and Kubernetes | PLT
• concept · Lightning Talk: Evaluating Scheduler Efficiency for AI/ML Jobs Using Custom Resourc... D. Shmulevich
• concept · Lightning Talk: Running Kind Clusters with GPU Support Using Nvkind - Evan Lezar, NVIDIA
• concept · Enabling Fault Tolerance for GPU Accelerated AI Workloads in Kubernetes - A. Singh & A. Paithankar
• concept · Improving Service Availability: Scaling Ahead with Machine Learning for HP... A. Sharma & E. Ramirez
• concept · Distributed Multi-Node Model Inference Using the LeaderWorkerSet API- Abdullah Gharaibeh, Rupeng Liu
• concept · WasmEdge: Cross-Platform, High-Performance, Lightweight, Embeddable Multi-Modal LLM Runtime | PLT. Presents WasmEdge as a lightweight, cross-platform, embeddable runtime for multi-modal LLMs.
• concept · WG Serving: Accelerating AI/ML Inference Workloads on Kubernetes - E.A. Gutierrez, Y. Tang
• concept · Harnessing the Power of Envoy Proxy for Building an LLM Gateway - Idit Levine, Solo.io
• concept · Cloud-Native AI: Wasm in Portable, Secure AI/ML Workloads - Miley Fu & Michael Yuan, Second State
• concept · Making Long-context LLM Inference 10x faster & 10x cheap... - Junchen Jiang, Yihua Cheng, & Zhou Sun
• concept · Managing and Distributing AI Models Using OCI Standards and Harbor - Steven Zou. Shows how to manage and distribute AI models using OCI standards and the Harbor registry.
• concept · Divide and Conquer: Master GPU Partitioning and Visualize Savings with OpenCost - Kaysie Yu
• concept · Efficient LLM Deployment: A Unified Approach with Ray, VLLM, and Kubernetes - Lily (Xiaoxuan) Liu
• tutorial · Tutorial: Get the Most Out of Your GPUs on Kubernetes with the GPU Operator
• tutorial · Tutorial: A Mad Scientist's Guide to Automating CNI with Generative AI - Doug Smith, Red Hat, Inc
• tutorial · Introduction to Distributed ML Workloads with Ray on Kubernetes - Mofi Rahman & Abdel Sghiouar
• panel · AI for Policy and Policy for AI! - P. Lamba, B. Kurktchiev, A. Suderman, R. Petty, J. Ray. Panel on using AI for policy and policy for AI.

2025 · KubeCon + CloudNativeCon China 2025 (Hong Kong)

• case study · Building Custom GPU Clusters at Scale: Using Kubespray To Create High-Perfor... Kay Yan & Rong Zhang
• concept · AI Model Distribution Challenges and Best... Wenbo Qi, Xiaoya Xia & Peng Tao, Wenpeng Li & Han Jiang
• concept · Defining a Specification for AI/ML Artifacts - Fog Dong, Peng Tao, Chlins Zhang & Xudong Wang
• concept · More Than Model Sharding: LWS & Distributed Inference - Peter Pan, Nicole Li & Shane Wang
• concept · Smart GPU Management: Dynamic Pooling, Sharing, and Scheduling for AI Work... Wei Chen & Mengxuan Li
• concept · Project Lightning Talk: K8s issue #52757: Sharing GPUs Among Multiple Containers - Xiao Zhang. Lightning talk on Kubernetes issue #52757 and sharing a GPU among multiple containers.
• concept · Lightning Talk: AI-Powered Kubernetes Diagnostics With K8sGPT - Kay Yan, DaoCloud. Lightning talk showing how K8sGPT uses AI to diagnose Kubernetes problems.
• concept · Lightning Talk: Dynamic GPU Fraction and Sharing With Cloud Native Principle - Tiejun Chen
• concept · Lightning Talk: Supercharge Agentic AI Apps: A DevEx-Driven Approach To Cloud Native S... Daniel Oh
• concept · Lightning Talk: Scaling AI With Wasm and Edge Computing - Miley Fu, WasmEdge. Lightning talk on using WasmEdge and Wasm to scale AI workloads at the edge.
• concept · New Pattern for Sailing Multi-host LLM Inference - Kante Yin, DaoCloud
• concept · Taming Dependency Chaos for LLM in K8s - Peter Pan, Neko Ayaka & Kebe Liu, DaoCloud. DaoCloud presents approaches to taming dependency chaos when running LLMs on Kubernetes.
• concept · Stability in Large Model Training: Practices in Software and Hardware Fault Self-Healing - Yang Cao

2025 · KubeCon + CloudNativeCon Europe 2025 - London

• case study · Kubernetes and AI To Protect Our Forests: A Cloud Native Infrastructure for Wildf... Andrea Giardini. Presents a cloud native infrastructure built on Kubernetes and AI for detecting wildfires to protect forests.
• case study · From High Performance Computing To AI Workloads on Kubernetes: M... Andrey Velichkevich, & Yuki Iwai
• case study · From Chaos To Control: Building ML Platform - George Markhulia & Steve Larkin, Volvo Cars — Volvo Cars
• case study · GPU Sharing at CERN: Cutting the Cake Without Losing a Slice! - Diana Gaponcic, CERN — CERN
• case study · Building & Operating a Large-scale HPC AI Cluster on Kubernetes - Kalyan Saladi & Chandan Avdhut. Speakers describe building and operating a large-scale HPC AI cluster on Kubernetes.
• case study · Project Lightning Talk: Revolutionizing Legacy Migrations with Konveyor AI - Jonah Sussman
• case study · AI Workload Preemption in a Multi-Cluster Scheduling System at Bloomberg - Leon Zhou & Wei-Cheng Lai — Bloomberg
• case study · Extending Kubernetes for AI | Lessons Learned From Platform... - Susan, Lucy, Andrea, Etienne, Tim — Lucy, Andrea, Etienne, Tim
• concept · Discover CNCF TAG Runtime: Advancing Cloud-Native Innovation from AI to Edge. Introduces CNCF TAG Runtime and its work spanning AI to edge.
• concept · Cloud Native AI: Harness the Power of Advanced Scheduling for High-P... William Wang & Xuzheng Chang
• concept · Transparent, Infra-Level Checkpoint and Restore for Resil... Ganeshkumar Ashokavardhanan & Bernie Wu. Presents transparent infrastructure-level checkpoint and restore for resilient workloads.
• concept · Testing AI Containers for Digital Twins in Science: A Cloud-HPC... Matteo Bunino & Diego Ciangottini
• concept · How To Supercharge AI/ML Observability With OpenTelemetry and Fluent Bit - Celalettin Calis
• concept · Unlocking How To Efficiently, Flexibly, Manage and Schedule Seven AI Chi... Xiao Zhang & Mengxuan Li
• concept · Optimizing Model Serving on Kubernetes With Model Streaming - Ekin Karabulut & Ronen Dar, Run:ai
• concept · AI Beyond Autocomplete: Using LLMs To Create 1000 Kubernetes... Justin Santa Barbara & Walter Fender
• concept · Green AI in Cloud Native Ecosystems: Strategies for Sustainability... Vincent Caldeira & Tamar Eilam
• concept · Generative AI Model Data Pre-Training on Kubernetes: A Use Case St... Alexey Roytman & Anish Asthana
• concept · Kubespray: Driving Cost-Efficiency for AI on Kubernetes - Antoine Legrand & Mohamed Zaian
• concept · Kubeflow Ecosystem: What’s Next for Cloud Native AI/ML and LLMOps
• concept · Redefining Access Control: Scaling Policy as Code for Humans and AI Agents - Raz Cohen, Permit.io
• concept · IAM, Agent: Identity for Autonomous AI - Matthew Bates, Cofide
• concept · Balancing Cost and Efficiency: Day2 Optimization of Multi-Cluster AI Infrastructure - Kevin Wang. Discusses day-2 optimization of multi-cluster AI infrastructure to balance cost and efficiency.
• concept · AI Pipelines With OPEA: Best Practices for Cloud Native ML Operati... Ezequiel Lanza & Melissa McKay. Covers best practices for building cloud native AI pipelines with OPEA.
• concept · A Practical Guide To Benchmarking AI and GPU Workloads in Kubernetes - Yuan Chen & Chen Wang
• concept · Enhancing CRI-O With CDI: Streamlining Device Integration in Kubernetes - Harshal Patil, Red Hat. Describes how CRI-O uses CDI to streamline device integration in Kubernetes.
• concept · Optimizing Training Performance for Large Language Model(LLM) in Kubernetes - Klaus Ma & Peng Gu
• concept · Advancements in AI/ML Inference Workloads on Kubernetes From... Yuan Tang & Eduardo Arango Gutierrez
• concept · Explain How Kubernetes Works With GPU Like I’m 5 - Carlos Santana, AWS
• concept · Asimov's Zeroth Law of Robotics: Observability for AI - Nicole van der Hoeven, Grafana Labs
• concept · Deep Dive To AI Agent Observability - Guangya Liu, IBM & Karthik Kalyanaraman, Langtrace AI. Deep dive into observability for AI agents.
• concept · The Explorer's Guide To Cloud Native GenAI Platform Engineering - Max Körbächer & Alexa Griffith. A guide to the landscape and building blocks of cloud native GenAI platform engineering.
• concept · Dashboards & Dragons: Crafting SLOs To Tame the AI Platform Cha... Alexa Griffith & Ankita Chaudhari
• concept · Orchestrating AI Models in Kubernetes: Deploying Ollama as a Nati... Samuel Veloso & Lucas Fernández
• concept · More Nodes, More Problems: Solving Multi-Host GPU/TPU Scheduli... John Belamaric & Morten Torkildsen
• concept · Slinky: Slurm in Kubernetes, Performant AI and HPC Workload Management in Kubernetes - Tim Wickberg
• concept · Scaling GPU Clusters Without Melting Down! - Alay Patel & Ryan Hallisey, NVIDIA
• concept · Securing AI Workloads: Building Zero-Trust Architecture for LLM Appl... Rohit Ghumare & Joinal Ahmed
• concept · Project Lightning Talk: Sailing Multi-Host Inference with LWS - Kante Yin, Maintainer
• concept · Project Lightning Talk: Extend Large Language Model Training Beyond Single Kubernetes Cl... Klaus Ma
• concept · Project Lightning Talk: Kubeflow Helm Chart - Krzysztof Romanowski, Maintainer
• concept · Project Lightning Talk: Scheduling AI Workload Among Multiple Clusters - Josh Packer, Supporter. Lightning talk on scheduling AI workloads across multiple Kubernetes clusters.
• concept · Project Lightning Talk: Spiderpool Updates For AI Workloads: DRA, NRI, and RDMA Obser... Weizhou Lan
• concept · Optimizing Metrics Collection & Serving When Autoscaling LLM Workloads - Vincent Hou & Jiří Kremser
• concept · Efficient Transparent Checkpointing of AI/ML Workloads in Kub... R. Stoyanov, A. Reber, V. Spišáková
• concept · Streamlined Efficiency: Unshackling Kubernetes Image Volumes for Rapid AI Model... E. Rey & Y. Yuan
• tutorial · Tutorial: Rock, Paper, Scissors! Build an AI-powered Interactive Game With Argo CD and Kubeflow
• tutorial · Tutorial: Build, Operate, and Use a Multi-Tenant AI Cluster Base... C. Misale, O. Tardieu & D. Grove. Hands-on tutorial on building, operating and using a multi-tenant AI cluster.
• keynote · OSS = Open Source ... Strategy!? Google Is Doubling Down on K8s in the AI Era, and Yo... ago Macleod. Google explains why and how it invests in Kubernetes and open source in the AI era.

2025 · KubeCon + CloudNativeCon India 2025

• case study · Scaling AI Like a Pro-PepsiCo’s LLM Deployment Strategy on K... Praseed Naduvath & Dhanashree Shetty — PepsiCo. PepsiCo describes its strategy for deploying and scaling LLMs on Kubernetes.
• case study · How Intuit Streamlined AI/ML Inference Workflows on K8s - Yashash H L & Sreekanth P R, Intuit — Intuit. Intuit explains how it streamlined its AI/ML inference workflows on Kubernetes.
• concept · Harbor Maintainers Talk - Role of Harbor in AI, IOT Edge and the Future - Prasanth Baskar, 8gears
• concept · Scaling Generative AI: Building Production-Ready LLM Applications - Daniel Oh, Red Hat
• concept · Cloud Native GenAI Using KServe and OPEA - Johnu George & Gavrish Prabhu, Nutanix. Shows how to build cloud native GenAI applications using KServe and OPEA.
• concept · Sandboxing Agentic AI With LSM-BPF - Rahul Jadhav, Accuknox
• concept · Multi-Layered Guardrails for Cloud Native AI: Enforcin... Vincent Caldeira & Anindita Sinha Banerjee
• concept · Auto-instrumentation for GPU Performance Using eBPF - Annanay Agarwal, Grafana Labs
• concept · Fine-Grained Authorization: The Missing Piece in Agentic AI Security - Shivay Lamba & Ashish Jha
• concept · Bridging Big Data and Machine Learning Ecosystems: A Cloud Native Approac... Johnu George & Shiv Jha. Shows a cloud native approach for bridging big data and machine learning ecosystems.

2025 · KubeCon + CloudNativeCon Japan 2025 (Tokyo)

• concept · Breaking Limits: Highly-Isolated and Low-Overhead Wasm Container - Soichiro Ueda & Ai Nozaki
• concept · Sailing Multi-host Inference for LLM on Kubernetes - Kay Yan, DaoCloud
• concept · Access AI Models Anywhere: Scaling AI Traffic With Envoy AI Gateway - Dan Sun & Takeshi Yoneda
• concept · Lightning Talk: VexLLM: Silence Negligible CVE Alerts Using LLM - Akihiro Suda, NTT
• concept · Scaling AI Responsibly: Building Et... Amita Sharma, Vincent Caldeira, Mohit Suman & Shamsher Ansari
• concept · Optimizing Data Locality and GPU Utilization for Training Workloads in Kubernetes - Bin Fan, Alluxio
• concept · Kubeflow Ecosystem: Un... Andrey Velichkevich, Luciano Resende, Yuki Iwai & Valentina Rodriguez Sosa
• concept · Beyond Stock Outs: Scaling Inference on Mixed GPU Hardware With DRA - John Belamaric & Bo Fu, Google. Shows how DRA can be used to scale inference across mixed GPU hardware and avoid stock-out issues.

2025 · KubeCon + CloudNativeCon North America 2025

• case study · From Pull To Predict: Accelerating AI Model Deployment on Kubernetes - Lucas Duarte & Tiago Reichert
• case study · Help! My LLM Is a Resource Hog: How We Tamed Inference With Kubernetes... Aditya Soni & Hrittik Roy
• case study · Unlocking Financial Progress: Credit Karma's AI Assista... Raj Kiran Gupta Katakam & Sukanya Moorthy — Credit Karma. Credit Karma describes building and running its AI assistant for financial guidance on its cloud native platform.
• case study · Taming the AI Hydra: Real-World Lessons in Governin... Brian Fox, Sarah Evans & Christopher Robinson
• case study · Models as Microservices, Platforms as Partners: Collaboratively Building ML Inf... Stephanie Pavlick. Describes how a platform team and ML teams collaborate to build ML inference, treating models as microservices.
• case study · Prepare for Disruptions: How We Upgrade the Whole ML Training Fleet Bi-week... Cong Gu & Ankit Goyal
• concept · AI Models Are Huge, but Your GPUs Aren’t: Mastering Multi-Node Distributed Infe... E. Wong & J. Shan
• concept · Benchmarking GenAI Foundation Model Inference Optimizations on Kubernetes - S.M. Varghese & B. Slabe
• concept · Kubeflow Ecosystem: Navigating the Cloud Native AI/ML and LLMOps Frontier - Multiple Speakers
• concept · SIG API Machinery and AI: What Comes Next? - Joe Betz, Google & David Eads, Red Hat
• concept · Beyond ChatOps: Agentic AI in Kubernete... Pavneet Ahluwalia, Idit Levine, Arik ALon & Valeria Ortiz. Explores agentic AI in Kubernetes operations, going beyond ChatOps.
• concept · GitOps for AI Agents: Building Reliable AI Pipelines With Argo - Benji Kalman & Shiran Melamed. Explains using GitOps with Argo to build reliable AI agent pipelines.
• concept · Effortlessly Build High-Performance AI/ML Processing Pipelines Within the ML Life... Kazuki Yamamoto. Shows how to build high-performance AI/ML processing pipelines across the ML lifecycle.
• concept · Intelligent Topology for AI Power: Network-Aware Scheduling Optimization With Volcano... Kevin Wang
• concept · High-Performance AI Workloads in KubeVirt VMs With NVIDIA GPUs: Ch... Ezra Silvera & Michael Hrivnak
• concept · Llm-d: Multi-Accelerator LLM Inference on Kubernetes - Erwan Gallen, Red Hat
• concept · Building AI/ML Pipelines on Kubernetes - Susan Wu, Ian Chakares, Lu Qiu, Anant Vyas & Lucy Sweet
• concept · Inference Awakens: Tools for the Age of GenAI - Alexa Griffith, Bloomberg & Erica Hughberg, Tetrate
• concept · LLMs on Kubernetes: Squeeze 5x GPU Efficiency With Cache, Route, Repea... Yuhan Liu & Suraj Deshmukh. Shows how caching, routing and replication on Kubernetes can improve GPU efficiency for LLM serving.
• concept · The Hidden Risks in AI/ML Supply Chains: How To Secure Your Workloads - Yash Pimple, Chainguard. Discusses supply chain risks in AI/ML workloads and how to secure them.
• concept · Dapr in 2026: Durable Execution and Resilient Eventing for AI Agents - Yaron Schneider & Rajesh Iyer. Dapr project update on durable execution and resilient eventing for AI agents.
• concept · An Open Source AI Compute Stack: Kubernetes + Ray + PyTorch + VLLM - Robert Nishihara, Anyscale. Describes an open-source AI compute stack built from Kubernetes, Ray, PyTorch and vLLM.
• concept · AI Inference Without Boundaries: Dynamic Routing With Multi-Cluster In... Rob Scott & Daneyon Hansen
• concept · Aligning Enterprise AI Security With MITRE ATLAS Using Op... Doron Caspin & Valentina Rodriguez Sosa
• concept · Istio Project Updates: AI Inference, Ambient Multicluster & Default Deny - Keith Mattix, Microsoft
• concept · Lightning Talk: Threat Modeling Kubernetes: Fast, Practical, and LLM-Driven - Maxime Coquerel. Lightning talk on fast, practical, LLM-driven threat modeling for Kubernetes.
• concept · Lightning Talk: Summarizing the Noise: LLM Observability With Open Data Hub, VLLM... Twinkll Sisodia
• concept · Lightning Talk: Tracing the Untraceable: OpenTelemetry for ‘Vibe-Coded’ LLM Apps - Pranay Prateek
• concept · Why Is My Query Slow? Real AI Use Cases With Vitess + Kubernete... Brett Warminski & Gourav Khanijoe
• concept · Partitionable Devices: Putting the “Dynamic” Back in... Morten Jæger Torkildsen & Jan-Philip Gehrcke. Describes partitionable devices in Kubernetes DRA for dynamic device allocation.
• concept · Optimizing Multi-Agent LLM Workloads With AMD GPUs and Kueue - Yuchen Fama, Jodie Su & Zhiming Shen
• concept · Navigating the AI/ML Networking Maze in Kubernetes: Lessons From the Trenches - Antonio Ojea, Google
• concept · Intelligent LLM Routing: A New Paradigm for Multi-Model AI Orchestration... Chen Wang & Huamin Chen
• concept · Deploying Lightweight AI Agents at the Healthcare Edge With K8s + Ollama - Gary Arora & Samarth Shah
• concept · Karmada in Action: Scaling AI Workloads Across Multi-Clus... Hongcai Ren, Tessa Pham & Wei-Cheng Lai
• concept · Securing AI Agent Infrastructure: AuthN/AuthZ Patterns for MCP and A2A - Yoshiyuki Tabata
• concept · Open Source at the Edge: Hardware, Firmware, and AI Stacks - Miley Fu & Saiyam Pathak
• concept · The Good, the Bad, and the Ugly: Hacking 3 Cloud Native AI Service... Hillai Ben-Sasson & Nir Ohfeld
• concept · Agent-Driven MCP for AI Workloads on Kubernetes - Ganeshkumar Ashokavardhanan & Qinghui Zhuang
• concept · Rage Against the Machine: Fighting AI Complexity With Kubernetes Simplicity - Paul Yu & Sachi Desai
• concept · Scaling Generative AI: Building Production-Ready LLM Applications - Daniel Oh & Kevin Dubois, IBM
• concept · Contributing To Kubernetes in an Age of AI - Mario F, Nabarun P, Priyanka S, Madhav J & Kaslin F
• concept · Meta’s Kubernetes-based Portable AI Research Environment - Shaun Hopper, Meta & Navarre Pratt
• concept · Routing Stateful AI Workloads in Kubernetes - Maroon Ayoub, IBM & Michey Mehta, Red Hat. Explains why standard Kubernetes load balancing fails for stateful LLM inference and how llm-d's cache-aware routing fixes it, with benchmark data.
• concept · Resilient by Design: Building Durable AI Agents on Kubernetes - Yaron Schneider, Diagrid
• concept · Highly Scalable AI Search Engine and AI Data Lake With Kubernetes and Lance... Lu Qiu & Chanchan Mao
• concept · Smarter Together: Orchestrating Multi-Agent AI Systems... Ana Maria Lopez Moreno & Sharon Camacho
• concept · Building a Closed-Source AI DevTool for Open Source and Enterprise - Devin Stein, Dosu
• concept · Simplifying Advanced AI Model Serving on Kubernetes Using Helm... Ajay Vohra & Tianlu Caron Zhang
• concept · RAG and Fine Tuning With Kubeflow - Francisco Javier Arceo, Red Hat & Andrey Velichkevich, Apple
• concept · Lessons Applied Building a Next-generation AI Proxy - John Howard, Solo.io
• concept · Hybrid-Confidential-Cloud: Democratize Secure AI With GPUs and Confidential Contain... Zvonko Kaiser
• concept · Project Lightning Talk: Bringing Agentic AI To Cloud Native With Kagent - Eitan Yarmush
• concept · Project Lightning Talk: Spiderpool: Dynamic Topology-Aware RDMA Allocation For GPU... Weizhou Lan
• tutorial · Tutorial: Unlock the Future of Kubernetes and Accelerators With Dynamic Resource Alloc... Rey Lejano. A hands-on tutorial on using Dynamic Resource Allocation to manage accelerators in Kubernetes.
• tutorial · Tutorial: Intelligent Failure: Using AI To Push Your Cluster To the Br... James Ilse & Michael Levan
• tutorial · Tutorial: A Cross-Industry Benchmarking Tutorial for Distributed LLM Inference... Multiple Speakers
• panel · In AI We Trust? Securing the Future, One Agent... Lin S, Yuval K, Hannah F, Andrew M & Ricardo A. Panel discussing how to secure AI agents and build trust in them.

2026 · Keynotes - KubeCon + CloudNativeCon Japan 2026

• concept · The Next Evolution of Kubernetes: GPU-Centric Infrastructure for AI Workloads - Takao Indoh, Fujitsu
• concept · Building a Multi-Tenant AI Platform with the CNCF Ecosystem - Aya Igarashi, Preferred Networks, Inc.
• concept · How Subaru Accelerated AI Model Development for Next-Generation EyeSight...- Ryoji Kobayashi, Subaru
• concept · Navigating the Identity Abyss in the AI‑Native Era - Yuichi Nakamura, Hitachi
• concept · How CNCF Projects United Two Countries' Engineers to Solve AI's Power-and-Land Problem - Kazuki Sato

2026 · KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026

• case study · Serving Qwen at Scale: Multi-Cluster AI Infrastructure on Karmada - Jionghang Cai, Alibaba — Alibaba
• case study · What We Learned Securing AI Agents at Scale on Multi-Tenant Kubernetes Clusters - Pengfei Ni
• case study · End-to-End Observability for LLM Inference: From Token To GPU - Jared Tan, Murphy Chen & Nicole Li — Murphy Chen
• case study · From Cloud to AI: How Kata Containers 4.0 Reinvents the Sandbox for the... Fupan Li & Xuewei Niu
• case study · Scaling Digital Employees at China Merchants Bank in Production: A Controlled AI... Jiahang Xu — China
• case study · Dragonfly's CNCF Graduation Journey and Large-Scale AI Model Distribution... Fengjun Lyu & Wenbo Qi
• case study · From Chatbots To Agentic AI: Running NVIDIA Dynamo the Kubernetes Way - Xianglong Lu & Bo Chu
• case study · Serving AI at Massive Scale: The Cloud Native Inference Plane Behind Huawei... Kevin Wang, Jun Ding — Massive
• concept · Open Source for the AI Era - Jonathan Bryce & Horace Li, The Linux Foundation
• concept · Tidal Auto-scaling for Training and Inference Based on Kubernetes + KEDA - Jun Zheng & Tan Pei Xiang
• concept · Ascend & PyTorch: Pioneer New AI Open Ecosystem - Liang Zhang, Huawei
• concept · PD Disaggregation VLLM Deployment on Alternative AI Accelerators Using Llm-d - 纪飞 王 & Mengxuan Li
• concept · What AI Agents Need From Open Infrastructure - Yaya Xia, Ant Group
• concept · Road from Kata Containers to Confidential Containers + GPUs: From First Commit to... Zvonko Kaiser. Traces the road from Kata Containers to Confidential Containers with GPU support.
• concept · Build a Unified Heterogeneous AI Computing Ecosystem for PyTorch - Zesheng Zong, Huawei. Presents an approach to a unified heterogeneous AI computing ecosystem for PyTorch on diverse hardware.
• concept · Meet the Community Behind the Open Source AI Stack - Panel
• concept · Building Frontier AI Infra: SGLang and Miles - Ke Bao, RadixArk
• concept · A Cloud Native Stack From Bare Metal To Tokens for Large-Scale AI Inference - Trong Vinh Nguyen. Presents a cloud native stack running from bare metal up to token serving for large-scale AI inference.
• concept · vLLM-Helion: SOTA LLM Performance by advanced autotuning and fine-grained dispatching - Sean Chen. Presents vLLM-Helion, which uses autotuning and fine-grained dispatching to reach state-of-the-art LLM inference performance.
• concept · Why Your TTFT Lies: Diagnosing PD-Disaggregated LLM Inference with Minimal... Nicole Li & Kebe Liu. Explains how to diagnose time-to-first-token in prefill/decode-disaggregated LLM inference.
• concept · Non-Invasive AI Agent Observability With OBI - Haibin Zhang, Alibaba Cloud & Endre Sara, Causely. Shows non-invasive observability of AI agents using OpenTelemetry eBPF instrumentation (OBI).
• concept · Turning Fragmented GPU Clusters Into One Elastic Compute Pool - ChongKang Tan, Ant Group
• concept · Training Through Failures: How Meta Keeps 100k-GPU Jobs Alive with... Tristan Rice & Amir Afzali
• concept · Secure AI Agent Sandboxing With OpenStack Zun and Kata Container - Wenjie Bao, ZTE
• concept · Redesigning OpenStack I18n for the AI Era: Weblate & Zero-GPU AI - Seongsoo Cho & DaGyeong Kim
• concept · Minutes, Not Weeks: Long-Term Memory for AI Applications With PowerMem - Yihang Li. Introduces PowerMem for giving AI applications long-term memory quickly.
• concept · Gravity of Ecosystems: Pollinating the Modern AI Orchestrator - Wenjia Zhang & Bo Fu, Google. Google speakers discuss how the open source ecosystem supports and shapes modern AI orchestration on Kubernetes.
• concept · Eliminating Adaptation Latency: Day-0 Inference for New Models on... Xiaoshuang Wang
• concept · Zero-Trust Traffic Governance for Kubernetes AI Agent Sandboxes - Bingshen Wang & Bo Kang Li
• concept · Building Portable Large Models on Heterogeneous AI... Mengsi Lyu, Hongjun Zhang & Yufeng Lyu
• concept · Can Stateful AI Agents Scale To Zero? - Peng Li, Alibaba Cloud
• concept · KV Cache: Accelerating AI Inference on Intel CPU - Bin Yang, Intel
• concept · Before vLLM starts: Preflight Checks for LWS for LLM Inference on K8S - Peter Pan, DaoCloud
• concept · Spec-Driven Evolution: How AI Agents are Rewriting the... Bertrand Souville & Muhammad Hamza
• concept · Hibernate and Evolving: Taming OpenClaw With OpenKruise Agents - Zhang Zhen, Alibaba Cloud. Shows how OpenKruise Agents can manage OpenClaw AI agents, including hibernation.
• concept · Dragonfly V2.5.0 - Intro, Updates, Data Distribution in AI Infrastructure - Wenbo Qi & Chenyu Zhang
• concept · Beyond Model Sharding: Atomic Scheduling and Disaggregated LLM Serving... Kay Yan & Chen Zicong
• concept · Evolving Argo Workflows for AI: New Features, Tuning, and Multi-Tenant... Shuangkun Tian & Yashi Su
• concept · Redefining LLM Training Through Atomic Components and Serverless TaaS - Tan Pei Xiang
• concept · KernelAgent: Hardware-Guided GPU Kernel Optimization via... Kaiming Cheng, Jack Khuu & Laura Wang
• concept · Beyond Static Pods: Dynamic GPU Sharing and Low-Latency Model Switching for LLM... 夕宁 & Jun Duan. Presents dynamic GPU sharing and low-latency model switching for LLM serving beyond static pods.
• concept · Helion's New CuTe DSL and Pallas Backends and How we Built Them via Agents - Dunfan Lu & Jason Ansel. Describes Helion's new CuTe DSL and Pallas backends and how they were built with AI agents.
• concept · How Intsig Serves Billions of Document Scans: GPU Virtualization at... Mengxuan Li & Walter Duan
• concept · Accelerating Sequential Recommender Models in the PyTorch Ecosystem - Zan Huang & Jiayu Sun, NVIDIA. Covers accelerating sequential recommender models in the PyTorch ecosystem.
• concept · Volcano: A Unified Scheduling Platform for Cloud Native AI - Chen Zicong, Huawei & DongYang Wang
• concept · Self-Healing Rollouts: Automating Production Fixes With Agentic AI - Kevin Dubois & Daniel Oh
• keynote · What Powers Frontier Intelligence - Thierry Carrez, OpenInfra Foundation. Keynote from the OpenInfra Foundation on the open infrastructure that powers frontier AI.

2026 · KubeCon + CloudNativeCon Europe 2026

• case study · Project Lightning Talk: From Idle to Ideal: Cross‑Cluster GPU Sharing with CoHDI - Takao Indoh
• case study · From Logs to Decisions: Autonomous AI Agents for Real-Time Kubernetes Threat R... Willem Berroubache
• case study · Is the Agent in the Room with Us Right Now? - Nick Rutigliano & Andrew Halaney, Netflix — Netflix. Netflix engineers share their own experience with AI agents operating in their environment and the challenges of knowing what agents are doing.
• case study · Making Topology-Aware Scheduling Practical for AI Workloads: From Discovery to Simula... Weizhou Lan
• case study · Virtualizing Large Scale GPU Cluster for Sovereign AI: Petasus AI Cloud Journey with Kube... Jian Li
• case study · LLM Inference at Scale: Orchestrating Prefill-Decode Disaggregation - Zhonghu Xu
• case study · Lessons Learned Orchestrating Multi-Tenant GPUs on OpenShift AI with NVIDIA KAI (G/H2... Luca Berton
• concept · Route, Serve, Adapt, Repeat: Adaptive Routing for AI Inference Workl... Nir Rozenbaum & Kellen Swain
• concept · Achieving Resilient Multi-Cluster AI Inference on Kubernetes With Kar... Wei-Cheng Lai & Han-Ju Chen
• concept · Lightning Talk: The $100K GPU Mystery: Why Your AI Training Dies at 99% - Michael Ifeanyi, Google
• concept · Cloud Native Theater | Istio Day: Running State of the Art Inference... Jackie Maertens and Nili Guy
• concept · Project Lightning Talk: OpenFGA For Agents: Safe Delegation In 5 Minutes - Andres Aguiar, Maintainer. Maintainer lightning talk showing how OpenFGA enables safe delegation of permissions to AI agents.
• concept · Cloud Native Theater | EnvoyCon: External Processing, Internal Leverage: MCP Tool Calls... Jens Kat. Shows how Envoy external processing can be used to handle MCP tool calls.
• concept · Project Lightning Talk: Konveyor AI for Every Language and the Future of App Moderniza... Shaaf Syed. Project lightning talk on Konveyor AI for application modernization across languages.
• concept · Cloud Native Theater | EnvoyCon: The Future of AI Traffic: What's New in Envoy AI Tra... Xiaolin Lin. Presents new features and the direction of Envoy AI Gateway for managing AI traffic.
• concept · Cloud Native Theater | Cloud Native University: AI + Kubernetes: What Beginners... Michael Forrester
• concept · Project Lightning Talk: Next-Gen AI Orchestration With Volcano On Kubernetes - Zhonghu Xu. A lightning talk on using Volcano for next-generation AI workload orchestration on Kubernetes.
• concept · Project Lightning Talk: Still Burning GPUs On Debugging? Scale AI In One Line - Anna Kramar
• concept · Project Lightning Talk: Scheduling at the Edge of Reason: Multi-Cluster AI & OCM - August Simonelli
• concept · Project Lightning Talk: Envoy Today: What’s New In Managing Cloud-Native And AI Workl... Karol Szwaj
• concept · Project Lightning Talk: Evolving KServe: The Unified Model Inference Platform For Both... Yuan Tang
• concept · Dragonfly V2.4.0 - Intro, Updates, Data Distribution in AI Infrastructure - Wenbo Qi & Chenyu Zhang
• concept · Collisions in the Dark: Illuminating the 95% of Kubeflow You Can't... Amine Lahouel & Laura Llinares
• concept · Redefining SLIs for LLM Inference: Managing Hybrid Cloud wit... Christopher Nuland & Hilliary Lipsig
• concept · Evolving Policy Management with Agentic AI: Kyverno MCP and Kagent for... Shuting Zhao & Dahu Kuang
• concept · Advancing Kubernetes AI Conformance: Current State and Road... Yuan Tang, Mario Fahlandt & Janet Kuo
• concept · Buildpacks: Towards 1.0, AI and Other Things - Aidan Delaney, Bloomberg
• concept · AI'm at the Gate! Introducing the AI Gateway Working G... Morgan Foster, Nir Rozenbaum & Shachar Tal
• concept · AI Agents & Platform Engineering: Efficiency Boost... Hasith K, Vincent C, Sara Q, Idit L & Carlos S
• concept · Cloud Native at the Far(m) Edge: Running Kubernetes and AI... Mauro Morales & Jordan Karapanagiotis
• concept · Hacking GPU Observability: eBPF & Ephemeral Containers in Action on Kubernetes - Brandon Kang
• concept · Explore TAG Workloads Foundation: Advancing Cloud Native Ex... Stephen R, Yuan T, Marlow W & Kante Y. Introduces the CNCF TAG Workloads Foundation and its work advancing cloud native workload practices.
• concept · BoF | Beyond Nginx Ingress: Higress as the K8s Gateway for the AI Era
• concept · Operationalizing AI Workloads on Kubernetes With OpenKruise - Zhang Zhen & Vec Sun. Shows how OpenKruise can be used to operate AI workloads on Kubernetes.
• concept · Peeking Into the GPU Black Box: Continuous Profiling on Kubernetes With eBPF - Zahari Dichev
• concept · Agentic Networking: Securing AI Agents on Kubernetes - Haiyan Meng, Google & Evaline Ju, IBM
• concept · The Latest in GPU, TPU, NIC and Other Device Support - WG Device Ma... John Belamaric & Patrick Ohly
• concept · REST in Peace: AI Needs to Be Async - Meet Asya - Artem Yushkovskiy, Delivery Hero
• concept · Linkerd: Reliable Production in an AI/MCP World - William Morgan, Buoyant
• concept · Optimizing LLM Inference for the Rest of Us - Abdel Sghiouar, Google
• concept · Securing the AI/ML Lifecycle With MLSecOps: Open Source Best... Bahaulddin Shammary & Andrey Shorov. Covers open source best practices for securing the AI/ML lifecycle with MLSecOps.
• concept · Lima Project Updates: Expanding the Focus To Hardening AI - Akihiro Suda, NTT & Anshuman Sahoo
• concept · To Swap or Not To Swap: Memory Management Design Patterns for AI Workloads in Kuber... Nic Vermande
• concept · Your Models Are Vulnerable: How KitOps Turns KServe Into a Zero-Tru... Brad Micklea & Gavrish Prabhu
• concept · Locking Down Ray Serve: How to Secure Ur ML Models? - Kateryna Hrytsaienko, Valtech
• concept · Instrumenting Kueue Scheduling for ML Training - Amy Chen, CoreWeave & Gabriel Saba, Google
• concept · Least-Privilege for AI: Authorizing Agents and MCP Tools with A... Luc Chmielowski & Nina Polshakova
• concept · Towards Building an Open Source AI Reference Stack for EU Sov... Madhav Bhargava & Sanjay Chatterjee
• concept · Continuous AI Conformance: The kOp... Arnaud Meukam, Janet Kuo, Justin Santa Barbara, Ciprian Hacman
• concept · Choose Your Own Adventure: AI Meets Internal Developer Platform - Whitney Lee & Viktor Farcic
• concept · Volcano: Orchestrating the Full AI Lifecycle – From Training To Inferen... Chen Zicong & Hajnal Máté
• concept · Breaking the Monolith: Decomposing and Governing Giant LLM Jobs Across Clusters - Kevin Wang, Huawei
• concept · Intelligent Routing for Optimized Inference - Antonio Berben, Solo.io & Felipe Vicens, Telefonica
• concept · Dapr in the AI Era: Orchestrating Complex Multi-agent Workflows With Automatic... Yaron Schneider. Shows how Dapr can orchestrate complex multi-agent AI workflows.
• concept · SIG Network: The State of Networking for AI on Ku... David M, Haiyan M, Bowei D & Kellen S & Nadia P
• concept · SIG API Machinery: SIG Updates and Deep Dive in the AI/ML Era - Stefan Schimanski, NVIDIA
• concept · Schema Inference and Automation: A New Era for Telemetry Mana... Nicolas Takashi & Arthur Silva Sens
• concept · Evolving KServe: The Unified Model Inference Platform for Both Predictive and... F. Spolti & J. Lee
• tutorial · Tutorial: DRA-matically Simple: On-Demand GPUs for MLOps - Doug Smith & Miguel Duarte Barroso
• tutorial · Introduction To Tag Infrastructure - Kashif Khan, Ericsson & Dylan Page, Lambda.ai
• tutorial · From Laptop to Cluster: Running AI Workloads Seamlessly from Podman... Ashley Cui & Urvashi Mohnani. Demonstrates moving AI workloads from a laptop with Podman to a Kubernetes cluster.
• tutorial · Tutorial: AI on Kubernetes Without the Chaos: Building Reproducible ML Environmen... Nourhan Mohamed
• panel · Kubeflow in Cloud Native AI: Orchestrati... Johnu G, Valentina S, Antonin S, Alexander P & Michael Z. Panel on Kubeflow's role in orchestrating cloud native AI workloads.

2026 · KubeCon + CloudNativeCon India 2026

• case study · LLMs Behind Bars: Sandboxes at Scale for AI on a Short Leash - Prashanth Pai, CodeRabbit — CodeRabbit
• case study · KServe in Production: Scaling Generative Inference the Cloud Native Way - Johnu George, Nutanix — Nutanix
• case study · Building a Self-Service Platform for Stateful AI Agents - Shuva Jyoti Kar, Cisco Systems — Cisco. Cisco describes building a self-service platform for running stateful AI agents.
• concept · A gRPC Transport for the Model Context Protocol - Pawan Bhardwaj, Google. Presents a gRPC transport design for the Model Context Protocol.
• concept · When Kubeflow Fights Cilium: Debugging 60% Idle GPUs... Ramkumar Nagaraj & Bingi Narasimha Karthik
• concept · The Hidden Cost of ML Data Lifecycles in Kubernetes - Yashasvi Misra, Pure Storage
• concept · Run Your Own AI Cluster on a DGX Spark: Kubernetes, GPUs, and DRA - Janakiram MSV & Shreyas Mocherla
• concept · GPU Hunter: Architecting Global GPU Availability With MultiKueue - Kishore Jagannath & Ram J A. Shows an architecture using MultiKueue to improve GPU availability across clusters globally.
• concept · Ready, Set, Go: WASM-Powered Containers Taking Your AI To New He... Anshika Tiwari & Abhineet Saxena
• concept · Zero Trust for Autonomous Agents: Isolating AI Workloads on Kubernetes - Kanagalingam Senthalan. Presents a zero trust approach to isolating autonomous AI agent workloads on Kubernetes.
• concept · Inference in Progress… Please Monitor Responsibly - Gaurav Sharma, NVIDIA
• concept · Sponsored Demo: Cut the Bill, Not the Brains. AI Coding Agents That Ship More and... Matas Kaminskas
• concept · Beyond Monolithic AI: Cloud Native Patterns for Dynami... Vincent Caldeira & Anindita Sinha Banerjee. Discusses cloud native patterns for moving beyond monolithic AI systems.
• concept · Building and Orchestrating Real Production-ready Agentic AI Systems - Kevin Dubois & Daniel Oh, IBM
• concept · Project Lightning Talk: ModelPack: Bringing the OCI Standard to AI/ML - Andrew Block, Maintainer
• concept · Beyond VLLM: Distributed LLM Inferencing With Llm-d on Kubernetes - Ravindra Patil, Red Hat
• concept · Sponsored Demo: Cloud Native AI: Model Management with Harbor & Velero - Dhruv Tyagi, Broadcom
• concept · When LLMs Hit Production: Why You Need an AI Gateway - Gavrish Prabhu, Nutanix
• concept · What Did My Agent Do? Observability and Accountability for AI Agents - Ishan Jain, Grafana Labs
• concept · Rab Ne Bana Di Jodi - Why Platforms & AI Need Each Other - Ram Iyengar, Cloud Foundry Foundation
• tutorial · So You Want To Run AI Agents on Kubernetes: A 101 Guide - Rajas Kakodkar, Broadcom. A 101 introduction to running AI agents on Kubernetes, covering the basic building blocks and considerations.
• panel · Observability 2.0: Shifting Left From Reactive Mon... Kokilavani K, RK Gupta, Sivakumar K & Suresh K. Panel with Intuit, Atlassian and Cloudera practitioners on the shift from traditional monitoring to LLM-assisted 'observability 2.0'.

2026 · KubeCon + CloudNativeCon Japan 2026

• case study · From Model Serving To Distributed Inference: How Llm-d Evolves AI Platforms on… K. Yan & L. He
• case study · Conformance for Inference: How We Reduced Bad Deploys on a GPU Platform - Aditya Soni & Hrittik Roy
• case study · Shared Yet Isolated at Scale: Building Multi-Tenant Inference Platform on… Y. Hiraki & Y. Tanaka
• case study · From Experiment To Enterprise: Scaling an AI Agent for Code Review - Adam Phan. Describes taking an AI code review agent from experiment to enterprise-scale use.
• case study · How To Evolve Your LLM Self-Hosting Platform: A Practical Guide To Adopting… S. Omura & Y. Zhan
• case study · Don't Start With 500 Clusters: Patterns in Scaling Multi-Cluster Kubernetes… N. Bora & M. Morrison. Speakers share patterns and lessons from scaling multi-cluster Kubernetes with Cluster API, arguing against starting with hundreds of clusters.
• concept · Designing a Hybrid AI Platform on Kubernetes - Aoi Kamide, NTT DOCOMO BUSINESS, Inc.
• concept · Beyond the DC Walls: Building a Nationwide GPU Fabric With KubeVirt and Wide-Area… K. Sato & J. Li
• concept · Who's Using That GPU? Identity-Aware Access Control for Kubernetes GPU… P. ONeill & K. Kushwaha
• concept · CoHDI: A CNCF Sandbox Project for Dynamic Hardware Composability in Kubernetes - Naoki Oguchi. Introduces CoHDI, a CNCF Sandbox project for dynamic hardware composability in Kubernetes.
• concept · SIG API Machinery in the Era of AI: Updates - Federico Bongiovanni, Google Cloud
• concept · Topology-Aware Scheduling for AI Training & Inference With Kueue - Michał Woźniak & Wei Huang
• concept · The Great Doubt: What Building an AI Agent Taught Us About Trust - Nicole van der Hoeven
• concept · Shared GPU Scheduling & Proactive Autoscaling: A Production Blueprint for 1000+… J. Kim & R. Jelveh
• concept · Scalable Security and Compliance in the Age of AI - Eddie Knight, Revanite
• concept · Project Lightning Talk: Lima in 5 Minutes: From Containers To AI Sandboxing - Ansuman Sahoo. A lightning talk introducing the Lima project and how it has moved from running containers to sandboxing AI workloads.
• concept · Project Lightning Talk: Spiderpool Unlocks Fine-Grained RDMA Observability for AI Inference - W. Lan
• concept · Project Lightning Talk: CoHDI: Dynamic Hardware Composition for AI‑Era Kubernetes… N. Oguchi
• concept · Beyond Single-Cluster Limits: Scaling GPU Workloads Across Kubernetes With… K. Das & E. Bayramova
• concept · Manufacturing Alerts To ReActive Agents: Self-Evolving AI Agents on K8S for Predictive… S. Moon. Presents self-evolving AI agents on Kubernetes that move manufacturing alerts toward predictive operation.
• concept · Open Source Meets Production MaaS: GMI Inference Engine and Karmada for Global AI… X. Wang
• concept · Kubeflow 2026 State of the Union: Orchestrating the Full ML Lifecycle - Y. Pal & V. Rodriguez Sosa
• concept · Sandbox for Agentic Application With Cloud Native Stack - Xu Wang, Ant Group & Yu Hu, JAPAN AI
• keynote · The State of Cloud Native: The Shift Towards AI - Katie Gamanji, Apple | CNCF. Keynote on the state of cloud native and the shift toward AI workloads.