Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

MAESTRO is an AI-powered research application designed to streamline complex research tasks.

bluetooth mesh chat, IRC vibes

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

Megatron's multi-modal data loader

The best OSS video generation models

Official inference framework for 1-bit LLMs

OCR, layout analysis, reading order, table recognition in 90+ languages

Swiss-army tool for scraping and extracting data from online assets, made for hackers

The best gradio web-ui for ai transcription, translation and TTS. Automatic subtitle creation using faster whisper. Easy one click installation. Fully portable.

转换网易云音乐 ncm 到 mp3 / flac. Convert Netease Cloud Music ncm files to mp3/flac files.

Fast and memory-efficient exact attention

All Documents for FoloToys

🔥🔥🔥 Web-based linux server management control panel. / 现代化、开源的 Linux 服务器运维管理面板。

#1 Locally hosted web application that allows you to perform various operations on PDF files

A low-latency & high-throughput serving engine for LLMs

SGLang is yet another fast serving framework for large language models and vision language models.

AI wearable necklace

使用Android原生开发的电视直播软件

Official Implementation of EAGLE-1 and EAGLE-2

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads