Kuaishou Tech
Author

Kuaishou Tech

Official Kuaishou tech account, providing real-time updates on the latest Kuaishou technology practices.

229
Articles
0
Likes
681
Views
0
Comments
Recent Articles

Latest from Kuaishou Tech

100 recent articles max
Kuaishou Tech
Kuaishou Tech
Nov 30, 2024 · Artificial Intelligence

Kuaishou and Tsinghua University Win First Prize in Qian Weichang Chinese Information Processing Award for Content Recommendation Technology

Kuaishou and Tsinghua University were honored with the first‑place Qian Weichang Chinese Information Processing Science and Technology Award for their collaborative content recommendation project, which achieved international‑level innovations in explainable recommendation, bias correction, and edge intelligence, and has been applied widely in Kuaishou's platform and top academic conferences.

Artificial IntelligenceFairnessKuaishou
0 likes · 5 min read
Kuaishou and Tsinghua University Win First Prize in Qian Weichang Chinese Information Processing Award for Content Recommendation Technology
Kuaishou Tech
Kuaishou Tech
Nov 27, 2024 · Artificial Intelligence

AI‑Driven User Experience Optimization in Kuaishou E‑commerce: Evolution, Practices, and Future Outlook

This article examines how Kuaishou’s e‑commerce platform leverages AI to analyze and improve B‑side user experience, detailing current challenges, the CPS metric model, a self‑built intelligent inspection platform, workflow automation, and future prospects for AI‑driven UX optimization.

AIAutomationIntelligent Inspection
0 likes · 17 min read
AI‑Driven User Experience Optimization in Kuaishou E‑commerce: Evolution, Practices, and Future Outlook
Kuaishou Tech
Kuaishou Tech
Nov 21, 2024 · Artificial Intelligence

Best Practices for Training Large Language Models on Ultra‑Large Scale Clusters

This article summarizes the challenges of distributed training for massive language models and presents a suite of solutions—including DP/TP/PP overlap, context parallelism, efficient recomputation, and a performance‑aware cost model—that together boost training throughput by over 30% on large GPU clusters.

GPU clustersPerformance Modelingactivation rematerialization
0 likes · 27 min read
Best Practices for Training Large Language Models on Ultra‑Large Scale Clusters
Kuaishou Tech
Kuaishou Tech
Oct 31, 2024 · Cloud Native

Stateful Service Cloud‑Native Practices: Kuaishou’s Redis on Kubernetes

This article examines the challenges and benefits of running stateful services such as Redis on Kubernetes, presents Kuaishou’s practical experience with cloud‑native migration, evaluates risks and performance impacts, and details the custom workloads, operators, federation and KubeBlocks solutions that enable large‑scale, reliable stateful service orchestration.

Cloud NativeFederationKubeBlocks
0 likes · 12 min read
Stateful Service Cloud‑Native Practices: Kuaishou’s Redis on Kubernetes
Kuaishou Tech
Kuaishou Tech
Oct 30, 2024 · Artificial Intelligence

Fast Mobile's AI Innovations at 2024 China Computer Conference

Fast Mobile showcased its AI model, 可灵AI, at the 2024 China Computer Conference, highlighting its achievements in generating over 3.7 billion videos and images, and announced a new research fund to foster academic-industry collaboration in AI.

AI ConferenceAIGCArtificial Intelligence
0 likes · 6 min read
Fast Mobile's AI Innovations at 2024 China Computer Conference
Kuaishou Tech
Kuaishou Tech
Oct 16, 2024 · Frontend Development

How Kola2d’s WebGL Engine Achieves 50+ FPS for Million‑Cell Spreadsheets

This article details the design and optimization of Kola2d, a custom WebGL rendering engine for Docs online spreadsheets, explaining why WebGL was chosen, how the system separates business and rendering layers, and the many performance tricks that enable smooth 50+ FPS rendering of tables with up to a million cells.

GPUKola2dOnline Spreadsheet
0 likes · 19 min read
How Kola2d’s WebGL Engine Achieves 50+ FPS for Million‑Cell Spreadsheets
Kuaishou Tech
Kuaishou Tech
Sep 27, 2024 · Artificial Intelligence

XPSR: Cross‑modal Priors for Diffusion‑based Image Super‑Resolution

The paper introduces XPSR, a diffusion‑based image super‑resolution method that incorporates cross‑modal semantic priors from a large multimodal language model, achieving state‑of‑the‑art performance on both reference and no‑reference quality metrics across synthetic and real‑world video restoration tasks.

AI researchECCV2024cross‑modal priors
0 likes · 8 min read
XPSR: Cross‑modal Priors for Diffusion‑based Image Super‑Resolution
Kuaishou Tech
Kuaishou Tech
Sep 20, 2024 · Artificial Intelligence

Building an LLM-Based Agent Platform for Enterprise Commercialization: Strategies, Architecture, and Practical Insights

This article details the strategic development and technical architecture of SalesCopilot, an LLM-driven agent platform designed for enterprise commercialization, highlighting the implementation of RAG and agent technologies, addressing practical challenges, and sharing key insights for building scalable AI applications.

AI agentsAI evaluationEnterprise AI
0 likes · 15 min read
Building an LLM-Based Agent Platform for Enterprise Commercialization: Strategies, Architecture, and Practical Insights
Kuaishou Tech
Kuaishou Tech
Sep 13, 2024 · Big Data

Blaze: Kuaishou’s Rust‑Based Vectorized Execution Engine for Spark SQL

Blaze is a Rust‑implemented, DataFusion‑based vectorized execution engine created by Kuaishou to accelerate Spark SQL queries, delivering up to 60% faster computation, 30% average compute‑power gains in production, and extensive architectural innovations such as native engine, protobuf protocol, JNI bridge, and Spark extension, while being open‑source and compatible with Spark 3.0‑3.5.

Big DataDataFusionRust
0 likes · 11 min read
Blaze: Kuaishou’s Rust‑Based Vectorized Execution Engine for Spark SQL
Kuaishou Tech
Kuaishou Tech
Jul 31, 2024 · Artificial Intelligence

Kuaishou’s Kolors Text‑to‑Image Model: Architecture, Evaluation, and Real‑World Applications

The article presents a comprehensive overview of Kuaishou’s Kolors (formerly 可图) multimodal generative model, detailing its data collection strategy, diffusion‑based architecture, evaluation metrics, derived capabilities such as prompt refinement and interactive generation, and a range of practical applications from AI‑powered live‑stream gifts to virtual try‑on, while also offering strategic advice for the domestic visual‑generation community.

AI applicationsKolorsdiffusion models
0 likes · 27 min read
Kuaishou’s Kolors Text‑to‑Image Model: Architecture, Evaluation, and Real‑World Applications