Stars
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
Web UI for OpenAvatarChat
A lightweight WebGL Render for LAM and LAM_Audio2Expression
[SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head
Colab for making Wav2Lip high quality and easy to use
洛曦 数字人视频播放器，带HTTP API，使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk，也可以用于播放本地视频
Demo for the "Talking Head Anime from a Single Image."
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
Xbotics 社区具身智能学习指南：我们把“具身综述→学习路线→仿真学习→开源实物→人物访谈→公司图谱”串起来，帮助新手和实战者快速定位路径、落地项目与参与开源。
NVIDIA Linux open GPU with P2P support
LLM Council works together to answer your hardest questions
Fast and memory-efficient exact attention
Deepseek-OCR&Paddle-OCR-VL 类openai协议的API
本專案提供一套使用 vLLM 高性能推理引擎和 Gradio WebUI 的 Docker 解決方案，旨在將 DeepSeek-OCR 這一尖端的視覺-語言模型 (VLM) 轉化為可供內部團隊協作使用的生產級服務。
Configs and boilerplates for Label Studio's Machine Learning backend
A quick vibe coded app for deepseek OCR
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Out-of-the-box DeepSeek OCR document parsing Web Studio
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
AIGCPanel 是一个简单易用的一站式AI数字人系统，支持视频合成、声音合成、声音克隆，简化本地模型管理、一键导入和使用AI模型。
A simple yet powerful agent framework that delivers with open-source models