NetEase Media Technology Team
Author

NetEase Media Technology Team

NetEase Media Technology Team

55
Articles
0
Likes
121
Views
0
Comments
Recent Articles

Latest from NetEase Media Technology Team

55 recent articles
NetEase Media Technology Team
NetEase Media Technology Team
Jan 15, 2024 · Mobile Development

iOS Information Feed Performance Optimization: Reducing Stuttering in Mobile Apps

iOS feed performance optimization reduced stuttering by moving layout and rendering off the main thread, using async text/image rendering, pre‑layout calculations, view hierarchy simplification, lightweight CALayers, and off‑screen rendering avoidance, boosting FPS from 35‑45 to 55‑60 on low‑end devices.

Async RenderingView HierarchyYYLabel
0 likes · 15 min read
iOS Information Feed Performance Optimization: Reducing Stuttering in Mobile Apps
NetEase Media Technology Team
NetEase Media Technology Team
Dec 22, 2023 · Mobile Development

Jetpack Compose: From MVVM to MVI Architecture in Android Development

The article guides Android developers through evolving UI architectures—from MVC to MVI—showing how to transition Jetpack Compose projects from MVVM to MVI, tackle hybrid navigation and WebView integration, and apply refactoring, performance tuning, and best‑practice code examples.

Android UIArchitecture PatternsHybrid Development
0 likes · 21 min read
Jetpack Compose: From MVVM to MVI Architecture in Android Development
NetEase Media Technology Team
NetEase Media Technology Team
Nov 6, 2023 · Artificial Intelligence

Overview of Sequential Recommendation Models

The article surveys sequential recommendation models from early non-deep approaches like FPMC, through RNN-based GRU4Rec and CNN-based Caser, to Transformer-based methods such as SASRec, BERT4Rec, TiSASRec, and recent contrastive-learning techniques, recommending SASRec or its variants for production use.

Deep LearningTransformercontrastive learning
0 likes · 17 min read
Overview of Sequential Recommendation Models
NetEase Media Technology Team
NetEase Media Technology Team
Aug 9, 2023 · Artificial Intelligence

GPU Model Inference Optimization Practices in NetEase News Recommendation System

The article outlines practical GPU inference optimization for NetEase’s news recommendation, covering model analysis with Netron, multi‑GPU parallelism, memory‑copy reduction, batch sizing, TensorRT conversion and tuning, custom plugins, and the GRPS serving framework to achieve significant latency and utilization gains.

GPU inferenceModel OptimizationProfiling
0 likes · 44 min read
GPU Model Inference Optimization Practices in NetEase News Recommendation System
NetEase Media Technology Team
NetEase Media Technology Team
May 23, 2023 · Cloud Native

How NetEase Media Scaled Flink with Kubernetes: Architecture, Optimizations, and Lessons Learned

This article details NetEase Media's migration of most Flink jobs to a self‑built real‑time platform on Kubernetes, covering the benefits of K8s isolation, the chosen native deployment mode, performance‑critical optimizations, monitoring, resource‑recommendation, and future directions for cloud‑native streaming workloads.

Cloud NativeFlinkKubernetes
0 likes · 20 min read
How NetEase Media Scaled Flink with Kubernetes: Architecture, Optimizations, and Lessons Learned
NetEase Media Technology Team
NetEase Media Technology Team
Mar 13, 2023 · Frontend Development

Progressive Upgrade Practice Based on Qiankun Micro-frontend Framework

The article details how a legacy Gulp‑AngularJS project with over 70 modules was progressively upgraded by introducing a new Angular 11 main application and using the qiankun micro‑frontend framework to host the old AngularJS code as a sub‑app, enabling route‑based mounting, menu sharing, CSS isolation, and low‑risk incremental migration.

AngularJs migrationFrontend Architecturemicro-frontend
0 likes · 10 min read
Progressive Upgrade Practice Based on Qiankun Micro-frontend Framework
NetEase Media Technology Team
NetEase Media Technology Team
Feb 13, 2023 · Game Development

How to Build a Dynamic Face‑Customization System on Mobile with Spine

This article explains how to use the Spine 2D skeletal animation framework to implement a flexible, runtime face‑customization and outfit‑changing feature on mobile platforms, covering basic concepts, code examples, resource handling, memory optimizations, and platform‑specific integration challenges.

Performance OptimizationResource ManagementSpine
0 likes · 22 min read
How to Build a Dynamic Face‑Customization System on Mobile with Spine
NetEase Media Technology Team
NetEase Media Technology Team
Dec 6, 2022 · R&D Management

Testing Challenges and Quality Assurance Improvements for News Recommendation Systems

To cope with the multi‑stage, feature‑rich and rapidly iterated NetEase News recommendation pipeline, the QA team introduced detailed stage logging, controllable recall and user‑profile injection, configurable filters, forced‑push mechanisms, an integrated performance‑testing platform, automated case configuration, centralized requirement tracking, and self‑test tools, dramatically boosting testing quality and efficiency while outlining future automation goals.

AutomationPerformance TestingR&D management
0 likes · 16 min read
Testing Challenges and Quality Assurance Improvements for News Recommendation Systems
NetEase Media Technology Team
NetEase Media Technology Team
Nov 17, 2022 · Backend Development

Design and Evolution of NetEase Advertising Engine Platform

NetEase’s advertising engine platform evolved from a monolithic, high‑concurrency system handling over a billion daily requests into a layered, distributed architecture that unifies indexing, billing, user‑tagging, and monitoring services, leverages Elasticsearch and custom extensions for fast retrieval, and plans further upgrades such as a custom retrieval kernel and Go‑based services.

Backend ArchitectureDistributed SystemsIndexing Service
0 likes · 21 min read
Design and Evolution of NetEase Advertising Engine Platform