Stars
DeepSeek Harness: Everything is a Plugin.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
Harmful content detection in memes — comparing BLIP-2 multimodal understanding vs CLIP+OCR pipeline for hateful meme classification (Reichman University, 2025)
分享AI Infra知识&代码练习：PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等
Wrapper of 50+ image matching models with a unified interface
🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型！A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）
A high-throughput and memory-efficient inference and serving engine for LLMs
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Minimal reproduction of DeepSeek R1-Zero
Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models
Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
Mini CCL - A lightweight collective communication library
modern AI for beginners
Model interpretability and understanding for PyTorch
AI powered open source recommender system engine supports classical/LLM rankers and multimodal content via embedding
The simplest, fastest repository for training/finetuning small-sized VLMs.
【A common used C++ & Python DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流
A pure go General-purpose Task-parallel Programming Framework
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step