Skip to main content

KServe Presentations and Demos

This page contains a collection of presentations, demos, and talks about KServe from various conferences, meetups, and community events. If you'd like to add a presentation or demo here, please send a pull request to the KServe website repository.

Conference Talks by Year​

2025​

EventTitleSpeaker(s)Resources
Cloud Native & Kubernetes AI Day North AmericaKServe Next: Advancing Generative AI Model ServingYuan Tang and Dan SunInfo
KubeCon North AmericaAnchoring Trust in the Age of AI: Identities Across Humans, Machines, and ModelsYuan Tang and Anjali TelangInfo
KubeConNavigating the Rapid Evolution of Large Model Inference: Where does Kubernetes Fit?Jiaxin Shan, Yuan Tang, Sergey Kanzhelev, Rita ZhangInfo
Cloud Native & Kubernetes AI Day EuropePanel: Engaging the Kubeflow Community: Building an Enterprise-Ready AI/ML PlatformYuan Tang, Andrey Velichkevich, Andreea Munteanu, Johnu George, Ronen DarVideo
KubeCon EuropeAdvancements in AI/ML Inference Workloads on Kubernetes From WG Serving and Ecosystem ProjectsYuan Tang, Eduardo Arango GutierezVideo
KubeCon EuropeKubeflow Ecosystem: What’s Next for Cloud Native AI/ML and LLMOpsJohnu George, Andrey Velichkevich, Yuki Iwai, Yuan Tang, Valentina RodriguezVideo
Red Hat SummitEmbracing Partnership and Open Collaboration in the Cloud-Native and AI Model Serving CommunitiesYuan Tang, Adam Tetelman, Brittany Rockwell, Tyler Michael SmithInfo
IBM TechXchangeKServe Deep Dive: Evolving Model Serving for the Generative AI EraYuan TangInfo

2024​

EventTitleSpeaker(s)Resources
KubeCon North AmericaUnlocking Potential of Large Models in ProductionYuan TangVideo
Cloud Native & Kubernetes AI Day North AmericaAdvancing Cloud Native AI Innovation Through Open CollaborationYuan TangVideo
Kubernetes Podcast from GoogleKubernetes Working Group ServingYuan Tang, Eduardo Arango GutierezPodcast
IBM TechXchangeKServe Essentials: Building a Production-Ready Cloud-Native Model Serving PlatformYuan TangInfo
PlatformConEngineering Cloud Native AI PlatformYuan TangVideo
Open Data Science ConferenceHighly Scalable Inference Platform for Models of Any SizeYuan TangInfo
KubeCon EuropeProduction-Ready AI Platform on KubernetesYuan TangVideo
KubeCon North AmericaEngaging the KServe CommunityAdam Tetelman, Taneem Ibrahim, Johnu George, Tessa Pham, Andreea MunteanuVideo
KubeCon EuropeFortifying AI Security in Kubernetes with Confidential ContainersSuraj Deshmukh, Pradipta BanerjeeVideo
KubeCon EuropeFrom Bash Scripts to Kubeflow and GitOps: Our Journey to Operationalizing ML at ScaleLuca Grazioli, Dennis OhrndorfVideo
KubeCon North AmericaProduction AI at Scale: Cloudera's Journey Adopting KServeZoram Thanga, Peter AbledaVideo
KubeCon North AmericaOptimizing Load Balancing and Autoscaling for LLM Inference on KubernetesDavid GrayVideo
KubeCon North AmericaBest Practices for Deploying LLM Inference, RAG and Fine Tuning PipelinesMeenakshi Kaushik, Shiva Krishna MerlaVideo
KubeCon EuropePlatform Building Blocks: How to Build ML Infrastructure with CNCF ProjectsYuzhui Liu, Leon ZhouInfo

2023​

EventTitleSpeaker(s)Resources
KubeCon EuropeThe State and Future of Cloud Native Model ServingDan Sun, Theofilos PapapanagiotouVideo
Kubeflow SummitScale your Models to Zero with Knative and KServeJooho LeeVideo
Kubeflow SummitWhat to choose? ModelMesh vs Model Serving?Vaibhav JainVideo

2022​

EventTitleSpeaker(s)Resources
KubeCon AI DaysExploring ML Model Serving with KServeAlexa Nicole GriffithVideo
KubeCon AI DaysEnhancing the Performance Testing Process for gRPC Model Inferencing at ScaleTed Chang, Paul Van EckVideo
KubeCon Edge DaysModel Serving at the Edge Made EasierPaul Van EckVideo
KnativeConHow We Built an ML inference Platform with KnativeDan SunVideo

2021​

EventTitleSpeaker(s)Resources
KubeCon AI DaysServing Machine Learning Models at Scale Using KServeYuzhui LiuVideo
KubeConServing Machine Learning Models at Scale Using KServeAnimesh SinghVideo
KubeCon ChinaAccelerate Federated Learning Model Deployment with KServeFangchi Wang & Jiahao ChenVideo

2020​

EventTitleSpeaker(s)Resources
NVIDIA GTCAccelerate and Autoscale Deep Learning Inference on GPUs with KFServingDan Sun, David GoodwinVideo
ICML WorkshopServerless inferencing on KubernetesClive CoxVideo
Serverless SummitServerless Machine Learning Inference with KFServingClive Cox, Yuzhui LiuVideo
Kubeflow DojoKFServing - Production Model Serving PlatformAnimesh Singh, Tommy LiVideo
Kubeflow DojoDemo - KFServing End to End through NotebookAnimesh Singh, Tommy LiVideo
Kubeflow DojoDemo - KFServing with Kafka and Kubeflow PipelinesAnimesh SinghVideo
Kubeflow CommunityKFServing - Enabling Serverless Workloads Across Model FrameworksEllis TarnVideo
Google CloudKubeflow 101: What is KFServing?Stephanie WongVideo
Anchor MLOpsMLOps Coffee Sessions - Serving Models with KubeflowDavid Aponte, Demetrios BrinkmannPodcast

2019​

EventTitleSpeaker(s)Resources
KubeConIntroducing KFServing: Serverless Model Serving on KubernetesDan Sun, Ellis TarnVideo
KubeConAdvanced Model Inferencing Leveraging KNative, Istio & Kubeflow ServingAnimesh Singh, Clive CoxVideo

Books and Publications​

Books​

"Distributed Machine Learning Patterns"​

  • Author: Yuan Tang
  • Publisher: Manning Publications
  • Description: Covers distributed machine learning patterns including model serving with KServe
  • Book Repository

Community Demos and Tutorials​

Live Demos and Tutorials​

"MLOps Meetup: KServe Live Coding Session"​

  • Speaker: Theofilos Papapanagiotou
  • Features Shown: Building a KServe deployment from scratch
  • Video