Legacy-Mess Detector – assess the “legacy-mess level” of your code and output a beautiful report

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

一种任务级GPU算力分时调度的高性能深度学习训练平台

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

The hardware design for AgiBot X1.

A high-performance runtime framework for modern robotics.

Productive, portable, and performant GPU programming in Python.

Simulation platform for general-purpose robotics & embodied AI learning.

A ros package for visualizing a robot face with different facial expressions

Bioregulatory Event Extraction using Large Language Models: A Case Study of Rice Literature

Jetson Nano Kernel Builder

Cross-platform, customizable ML solutions for live and streaming media.

Open source code for AlphaFold 2.

Reasonably fast (compared to cublas) and relatively simple int8 tensor core gemm

DIY Doly project

ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

The Modular Platform (includes MAX & Mojo)

ROS package used to create an endpoint to accept ROS messages sent from a Unity scene using the ROS TCP Connector scripts

Central repository for tools, tutorials, resources, and documentation for robotics simulation in Unity.

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

real time face swap and one-click video deepfake with only a single image

Python SDK for Meta Marketing APIs

手机App爬虫

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

SGLang is a high-performance serving framework for large language models and multimodal models.

A high-throughput and memory-efficient inference and serving engine for LLMs