AI Personal Learning
and practical guidance
CyberKnife Drawing Mirror
Total 992 articles

Tags: ai open source projects Page 16

DualPipe: a bi-directional pipelined parallel algorithm to improve the efficiency of large-scale AI model training (DeepSeek Open Source Week Day 4)

General Introduction DualPipe is an open source technology developed by the DeepSeek-AI team focused on improving the efficiency of large-scale AI model training. It is an innovative bi-directional pipelined parallel algorithm primarily used to achieve complete overlap of computation and communication in DeepSeek-V3 and R1 model training, with...

DeepGEMM:高效支持FP8矩阵运算的开源库(DeepSeek 开源周第三天)-首席AI分享圈

DeepGEMM: An Open Source Library with Efficient Support for FP8 Matrix Operations (DeepSeek Open Source Week Day 3)

General Introduction DeepGEMM is an open source FP8 GEMM (Generalized Matrix Multiplication) library developed by the DeepSeek team, focused on providing efficient support for matrix operations. It is specifically designed for the Tensor Core of the NVIDIA Hopper architecture and supports both common matrix operations and mixed expert models (MoE)...

Coding-Tutor:提供个性化编程指导的智能教学助手-首席AI分享圈

Coding-Tutor: an intelligent teaching assistant that provides personalized programming instruction

General Introduction Coding-Tutor is an open source project hosted on GitHub and created by developer iwangjian to provide learners with a personalized programming teaching experience. It uses conversational artificial intelligence technology to dynamically adjust teaching content based on the user's knowledge background and learning progress, helping...

TRV:将幻灯片/PPT和讲解备注快速生成演讲视频-首席AI分享圈

TRV: Rapidly Generate Presentation Videos from Slides/PPTs and Explanatory Notes

General Introduction TRV is an open source tool, hosted on GitHub, designed to help users quickly convert slides and lecture notes into videos with narration. It automatically generates audio and video content from incoming presentation files through simple command line operations, suitable for those who need to quickly create presentation videos for teaching...

LazyLLM:商汤开源构建多智能体应用的低代码开发工具-首席AI分享圈

LazyLLM: Shangtang's open source low-code development tool for building multi-intelligence body applications

Comprehensive Introduction LazyLLM is an open source tool developed by the LazyAGI team, focusing on simplifying the development process of multi-intelligence large model applications. It helps developers quickly build complex AI applications and save time on tedious engineering configurations through one-click deployment and lightweight gateway mechanisms. Whether you are a beginner...

MagicArticulate:将静态3D模型生成骨骼结构动画资产-首席AI分享圈

MagicArticulate: generating skeletal structure animation assets from static 3D models

Comprehensive Introduction MagicArticulate is an AI framework developed by ByteDance in collaboration with Nanyang Technological University (NTU), focusing on rapidly transforming static 3D models into animation-enabled digital assets. It automatically generates skeletal structures and skinning rights for models through advanced autoregressive Transformer and functional diffusion modeling...

en_USEnglish