Stars
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi…
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
TradingAgents: Multi-Agents LLM Financial Trading Framework
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构…
My learning notes for ML SYS.
[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、FastAPI 搭…
Fast and memory-efficient exact attention
Universal cross-platform tokenizers binding to HF and sentencepiece
Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型
Stable Diffusion web UI
A latent text-to-image diffusion model
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Universal LLM Deployment Engine with ML Compilation
中文langchain项目|小必应，Q.Talk，强聊，QiangTalk
Cross-platform, customizable ML solutions for live and streaming media.
A high-fidelity 3D face reconstruction library from monocular RGB image(s)
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
Examples and guides for using the OpenAI API
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Making large AI models cheaper, faster and more accessible
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）