This article introduces Kubeflow, a Kubernetes‑based machine‑learning platform, outlines the typical ML lifecycle, details core components, explains why Kubernetes benefits AI workloads, and provides a step‑by‑step guide for installing and accessing Kubeflow’s services, concluding with its industry impact.
The article presents a comprehensive overview of the WPAI (Wuba Platform of AI) architecture, detailing its machine‑learning and deep‑learning components, feature‑engineering framework, distributed training pipelines, online prediction services, and deployment on Kubernetes‑managed GPU/CPU resources to accelerate AI applications across 58.com business lines.
DeepInsight is a distributed, micro‑service‑based platform that provides end‑to‑end data exposure, multi‑dimensional visual analysis, and interactive debugging for TensorFlow models, turning opaque neural networks into transparent, controllable systems through real‑time visualizations, dynamic data sets, and integrated lifecycle management.
The article introduces Ctrip’s Model Engine Platform, a comprehensive system that streamlines feature preparation, engineering, model management, and product orchestration to enable fast, reliable real‑time AI model serving across various business scenarios, while addressing common challenges such as manual data handling, offline‑only prediction, and long development cycles.
Intelligent Titanium TI-ONE is a one‑stop ML IDE on Tencent Cloud offering integrated data preparation, drag‑and‑drop algorithm development, automatic hyperparameter tuning, multi‑level collaboration, one‑click model deployment, and support for major frameworks such as TensorFlow, PyTorch, Angel and XGBoost, plus commercial features via GaiaStack.
In 2017 Alibaba's AliMe chatbot platform expanded from a single‑company solution to a multilingual, multi‑channel AI service, introducing platform‑level SaaS/PaaS capabilities, a seven‑layer front‑end architecture, modular back‑end design, advanced intent recognition, knowledge‑graph‑driven product management, reinforcement‑learning‑based recommendation, and machine‑reading comprehension for enterprise and consumer use cases.
Since September 2016, JD’s AI foundation platform has leveraged Docker and Kubernetes to build a scalable machine‑learning infrastructure that now runs over 5,000 container instances, supports more than 20 AI services, and provides unified GPU, storage, networking, and multi‑tenant capabilities for both inference and training workloads.
This article details JD's AI platform built on Docker and Kubernetes, covering its high‑availability architecture, network plugin choices, storage solutions like GlusterFS and SeaweedFS, GPU management, CI/CD pipelines, logging, monitoring, and native Spark on Kubernetes, illustrating how a cloud‑native stack supports large‑scale AI services.
