Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

AI 原生应用开发实战：基于模型上下文协议MCP AI Native Application Development In Action: Based On Model Context Protocol

Visual testing tool for MCP servers

Model Context Protocol Servers

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

A lightweight, powerful framework for multi-agent workflows

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

TTS Towards Human-Sounding Speech

A collection of MCP clients.

Pioneering Multimodal Reasoning with CoT

Build your own AI friend

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 15+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

Repository contains Playwright Model Context Protocol to automate Browser and APIs

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Awesome Reasoning LLM Tutorial/Survey/Guide

The official Soundwave repository

这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

A TypeScript framework for building MCP servers.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

All the code and materials related to our YouTube channel (TwoSetAI)

[ICLR 2025 Oral] TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding and Diffusion Interpolation

The Triton TensorRT-LLM Backend

企业级RAG系统从入门到精通

Awesome MCP Servers - A curated list of Model Context Protocol servers

All-in-One Development Tool based on PaddlePaddle（飞桨低代码开发工具）

A lightweight framework for building LLM-based agents