Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Best practices & guides on how to write distributed pytorch training code

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

A framework for few-shot evaluation of language models.

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…

记录我在cs336学习时的笔记和作业

基于Python的开源量化交易平台开发框架

[NeurIPS D&B '25] The one-stop repository for LLM unlearning

slime is an LLM post-training framework for RL Scaling.

Nano vLLM

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

A Zotero plugin for syncing items and notes into Notion

[CVPR2024] MMA-Diffusion: MultiModal Attack on Diffusion Models

《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！

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

A high-throughput and memory-efficient inference and serving engine for LLMs

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

🤗 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.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Crack LeetCode, not only how, but also why.

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.

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）