Stars
Z-library，官方Z-lib镜像网址及入口(2026/6/7)
中国专利.skill：专利点挖掘与交底书（发明/实用/外观）编写，通俗解读专利，嗅探政策动向，辅助审查答复。
Scripts and doc for https://www.dolthub.com/repositories/chenditc/investment_data
AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库
欢迎来到电子书下载宝库，一个汇聚了各类电子书下载链接的地方。无论你是喜欢阅读经典文学、经管励志、终身学习、职场创业、技术手册还是其他类型的书籍，这里都能满足你的需求。 该库涵盖了帆书app(原樊登读书)、微信读书、京东读书、喜马拉雅等读书app的大部分电子书。
⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。
Stable Diffusion web UI
Real-time face swap for PC streaming or video calls
Boosting 4-bit inference kernels with 2:4 Sparsity
👨💻 An awesome and curated list of best code-LLM for research.
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
🙌 OpenHands: AI-Driven Development
OneDiff: An out-of-the-box acceleration library for diffusion models.
[ICML 2024] CLLMs: Consistency Large Language Models
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese
VideoSys: An easy and efficient system for video generation
SGLang is a high-performance serving framework for large language models and multimodal models.
Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.