Lists (15)
Starred repositories
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
A collection of various awesome lists for hackers, pentesters and security researchers
Papers from the computer science community to read and discuss.
An open-source AI agent that brings the power of Gemini directly into your terminal.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
Official inference framework for 1-bit LLMs
A collection of modern/faster/saner alternatives to common unix commands.
Professional Antigravity Account Manager & Switcher. One-click seamless account switching for Antigravity Tools. Built with Tauri v2 + React (Rust).专业的 Antigravity 账号管理与切换工具。为 Antigravity 提供一键无缝账号切…
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Daemon to ban hosts that cause multiple authentication errors
GameStream client for PCs (Windows, Mac, Linux, and Steam Link)
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
[Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
FlashMLA: Efficient Multi-head Latent Attention Kernels
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
Hackable and optimized Transformers building blocks, supporting a composable construction.
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
DeepEP: an efficient expert-parallel communication library
High-speed Large Language Model Serving for Local Deployment
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Tools for merging pretrained large language models.
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels