Stars
Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
State-of-the-Art Text Embeddings
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer
An open-source RAG-based tool for chatting with your documents.
Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS
SGLang is a fast serving framework for large language models and vision language models.
A simple, easy-to-hack GraphRAG implementation
RAG that intelligently adapts to your use case, data, and queries
A library for efficient similarity search and clustering of dense vectors.
GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Efficient Retrieval Augmentation and Generation Framework
A modular graph-based Retrieval-Augmented Generation (RAG) system
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Triton Documentation in Chinese Simplified / Triton 中文文档
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
短信转发器——监控Android手机短信、来电、APP通知,并根据指定规则转发到其他手机:钉钉群自定义机器人、钉钉企业内机器人、企业微信群机器人、飞书机器人、企业微信应用消息、邮箱、bark、webhook、Telegram机器人、Server酱、PushPlus、手机短信等。包括主动控制服务端与客户端,让你轻松远程发短信、查短信、查通话、查话簿、查电量等。(V3.0 新增)PS.这个APK…
An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.
⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.