Stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
⭐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 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对…
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
A book-in-progress about the Linux kernel and its insides.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Fast and memory-efficient exact attention
基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
Modular visual interface for GDB in Python
Automatic CPU speed & power optimizer for Linux
Transformer: PyTorch Implementation of "Attention Is All You Need"
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
A simple code complexity analyser without caring about the C/C++ header files or Java imports, supports most of the popular languages.
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
Pytorch Implementations of large number classical backbone CNNs, data enhancement, torch loss, attention, visualization and some common algorithms.
Helpful kernel tutorials and examples for tile-based GPU programming
一个让 AI 模型在真实市场中进行实盘交易与对抗的实验平台。目标是通过不断迭代，让智能体真正学会在不确定市场中生存和盈利。
Mantella is a Skyrim and Fallout 4 mod which allows you to naturally speak to NPCs using Whisper (speech-to-text), LLMs (text generation), and Piper / xVASynth / XTTS (text-to-speech).
Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tools
NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading