REverse-Engineered Reasoning for Open-Ended Generation

Free full-featured web-based audio & waveform editing tool (with AI features)

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

llama.cpp fork with additional SOTA quants and improved performance

Croco.Cpp is fork of KoboldCPP infering GGML/GGUF models on CPU/Cuda with KoboldAI's UI. It's powered partly by IK_LLama.cpp, and compatible with most of Ikawrakow's quants except Bitnet.

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

The easiest way to edit images in one prompt

Emulating Apple Silicon devices.

xllamacpp - a Python wrapper of llama.cpp

Lets make loop video diffusion practical!

A ComfyUI extention for BAGEL dfloat11 Quantized wrapper (Unified Model for Multimodal Understanding and Generation)

这是一个基于Model Context Protocol (MCP)的服务器，用于根据用户任务需求提供预设的prompt模板，帮助Cline/Cursor/Windsurf...更高效地执行各种任务。服务器将预设的prompt作为工具(tools)返回，以便在Cursor和Windsurf等编辑器中更好地使用。

Real time streaming digital human based on nerf

Fork of the Triton language and compiler for Windows support and easy installation

Lightweight coding agent that runs in your terminal

Fetch an entire site and use it as an MCP Server

基于 Vue + FastAPI + AKShare 的开源量化分析

Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model

开源量化分析

A set of nodes to edit videos using the Hunyuan Video model

Manage and switch between multiple proxies quickly & easily.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

SPO | Self-Supervised Prompt Optimization

API server for F5-TTS

口袋AI，将世界知识装进口袋。pocketpal-ai 中文版

✍ WeChat Markdown Editor | 一款高度简洁的微信 Markdown 编辑器：支持 Markdown 语法、自定义主题样式、内容管理、多图床、AI 助手等特性

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

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Un motor de búsqueda potenciado por IA con una interfaz de usuario generativa, impulsado por MALLO (MultiAgent LLM Orchestrator).