Lists (6)
Starred repositories
Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.
⚡ A Fast, Extensible Progress Bar for Python and CLI
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
🦜🔗 Build context-aware reasoning applications
LlamaIndex is the leading framework for building LLM-powered agents over your data.
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
使用Github Action自动编译一加多种KernelSU分支内核并手动发布稳定构建
SGLang is a fast serving framework for large language models and vision language models.
Using system APIs directly with adb/root privileges from normal apps through a Java process started with app_process.
LLMs-from-scratch项目中文翻译
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
JingMatrix / LSPosed
Forked from LSPosed/LSPosedLSPosed Framework resuscitated
PyTorch building blocks for the OLMo ecosystem
Maximize the potential of Cursor best practices for Automatic Rule and Custom Agent Generation and Agile Workflows
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Transpile curl commands into Python, JavaScript and 27 other languages
The official Typescript SDK for Model Context Protocol servers and clients
The simplest docker file of Confluence. Support v8.9.8(latest) v9.2.1(latest) and v8.5.19(lts)
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。
An Open Source Machine Learning Framework for Everyone