Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Simultaneous speech-to-text model

A research prototype of a human-centered web agent

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

BoxMOT: Pluggable SOTA multi-object tracking modules modules for segmentation, object detection and pose estimation models

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Brython (Browser Python) is an implementation of Python 3 running in the browser

[AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"

Supercharge Your LLM with the Fastest KV Cache Layer

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale

Inference and training library for high-quality TTS models.

Familiar asyncio ORM for python, built with relations in mind

The SQL IDE for Your Terminal.

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

⛹️ Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

GPU cluster manager for optimized AI model deployment

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

A fast admin dashboard based on FastAPI and TortoiseORM with tabler ui, inspired by Django admin

Run PyTorch LLMs locally on servers, desktop and mobile

SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection

A Repo For Document AI

Memory infrastructure for LLMs and AI agents