Kubernetes Wonderland: Adventures in Platform Building
探讨Kubernetes平台构建的挑战与机遇,聚焦用户需求与工具抽象,对比开发和机器学习平台,并通过演示展示如何利用开源工具构建高效平台。
DevOps in Data Science - What Works and What Doesn't
Explore challenges and solutions in implementing DevOps for data science projects, focusing on balancing ML engineers' needs with data scientists' desire for simplicity using Kubeflow and other tools.
From Bash Scripts to Kubeflow and GitOps - Operationalizing ML at Scale
Explore the journey of operationalizing data science workloads at scale using Kubeflow and GitOps, from initial challenges to a standardized approach for ML experiments, API creation, and batch predictions delivery.
Production-Ready AI Platform on Kubernetes
Explore best practices for building scalable AI/ML platforms using cloud-native technologies like Kubernetes, Kubeflow, and KServe. Learn to tackle challenges in MLOps and large model inference systems.
Cloud Native Artificial Intelligence - Top to Bottom
Explore how Cloud Native is shaping MLOps implementations, focusing on tools like Kubeflow and KServe. Learn to leverage Cloud Native knowledge for AI integration and future developments.
Enhancing the Performance Testing Process for gRPC Model Inferencing at Scale
Explore performance testing for gRPC model inferencing at scale using Kubernetes, KServe, and ModelMesh. Learn about deployment, load testing, and monitoring key metrics.
Model Serving at the Edge - Challenges and Solutions with ModelMesh
Explore efficient AI model deployment on edge devices using ModelMesh, K3s, and MicroShift. Learn to overcome resource limitations and manage multiple models effectively for large-scale adoption.
AI-Ready Microservice Architecture for Deploying and Evaluating AI Models
Explore event-driven architecture for deploying AI models in production using Knative, KServe, and Kubeflow. Includes real-time image recognition demo with audience participation.
ModelMesh: Scalable AI Model Serving on Kubernetes
Explore scalable AI model deployment on Kubernetes using ModelMesh, a multi-model serving backend for KServe. Learn about its architecture, monitoring, and new features for efficient, high-density model serving.
Fortifying AI Security in Kubernetes with Confidential Containers - CoCo
Explore confidential computing for AI model protection in Kubernetes using Confidential Containers (CoCo). Learn how CoCo enhances security for AI/ML workloads and provides memory protection for foundational platforms.
Building an ML Inference Platform with Knative - Serverless Containers on Kubernetes
Leveraging Knative for scalable ML inference platforms: simplifying deployment, enabling serverless containers, and optimizing performance for production-ready machine learning applications.
Exploring ML Model Serving with KServe - Features and Use Cases
Discover KServe's ML model deployment capabilities, from basic serving to advanced features like inference graphs and ModelMesh, enhancing efficiency for data scientists and engineers.
Training AI to Code Using Project CodeNet - Largest Code Dataset
Explore Project CodeNet's vast code dataset and learn how to leverage it for machine learning tasks using MLX, including code classification and complexity analysis on Kubernetes.
How Bloomberg Uses AI to Speed Up Over-the-Counter Trading
Explore how Bloomberg leverages AI and Kubernetes to enhance over-the-counter trading efficiency, focusing on detecting offers in group chats and streamlining negotiations for traders.
The State and Future of Cloud-Native Model Serving
Explore KServe's progress, latest developments, and future roadmap for cloud-native ML model serving. Learn about Kubernetes design patterns and CNCF ecosystem integration for production model deployment.
Machine Learning in Fastly's Compute@Edge
Explore WebAssembly modules for efficient ML model execution in Fastly's Compute@Edge, covering wasi-nn extensions, host API revisions, and KServe protocol integration for enhanced performance.
Integrating High Performance Feature Stores with KServe Model Serving
Explore high-performance feature stores integration with KServe for efficient ML model serving, focusing on Feast concepts, KServe challenges, and scalable architectures.
Serving Machine Learning Models at Scale Using KServe
Explore KServe's Multi-Model Serving solution for scalable machine learning deployment. Learn design, implementation, and benchmarks for efficient model serving across frameworks.
MLSecOps - Automated Online and Offline ML Model Evaluations on Kubernetes
Explore MLSecOps on Kubernetes: Automate real-time and offline ML model evaluations using KServe, Knative, Apache Kafka, and Trusted-AI tools for enhanced security and monitoring in production environments.
Creating a Custom Serving Runtime in KServe ModelMesh - Hands-On Experience
Learn to create custom serving runtimes in KServe ModelMesh for ML model deployment. Explore key features, build container images, and run predictions using custom runtimes in this hands-on tutorial.
Efficient Integration of Kubeflow Tools - ISS Data Case Study on Anomaly Detection
Explore Kubeflow's integrated tools for ML workflows through an ISS anomaly detection case study, showcasing Dask, Katib, PyTorch Operator, and KServe in a unified KFP pipeline.