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.
Crack LeetCode, not only how, but also why.
A high-throughput and memory-efficient inference and serving engine for LLMs
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
📖 NEW BOOK (/bin/zsh.99 launch): https://amzn.to/4cvxqSw — This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems.
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
verl: Volcano Engine Reinforcement Learning for LLMs
An all-in-one enhancement suite for Google Gemini & AI Studio - timeline navigation, folder management, prompt library, and chat export in one powerful extension. / Google Gemini & AI Studio 全能增强插件…
A framework for few-shot evaluation of language models.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
slime is an LLM post-training framework for RL Scaling.
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
A Zotero plugin for syncing items and notes into Notion
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
About Awesome things towards foundation agents. Papers / Repos / Blogs / ...
分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等
Existing Literature about Machine Unlearning
《EasyOffer》（<大模型面经合集>）是针对LLM宝宝们量身打造的大模型暑期实习Offer指南，主要记录大模型暑期实习和秋招准备的一些常见大厂手撕代码、大厂面经经验、常见大厂思考题等；小白一个，正在学习ing......有问题各位大佬随时指正，希望大家都能拿到心仪Offer！
[NeurIPS D&B '25] The one-stop repository for LLM unlearning