Deploy open-source LLMs on AWS in minutes — with OpenAI-compatible APIs and a powerful CLI/SDK toolkit.

Fully open reproduction of DeepSeek-R1

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

Powering AWS purpose-built machine learning chips. Blazing fast and cost effective, natively integrated into PyTorch and TensorFlow and integrated with your favorite AWS services

Example code for AWS Neuron SDK developers building inference and training applications

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

IDM-VTON-training : This is an unofficial training code of idm-vton

🦜🔗 The platform for reliable agents.

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

Amazon SageMaker Local Mode Examples

The official Meta Llama 3 GitHub site

Llama3-Tutorial（XTuner、LMDeploy、OpenCompass）

LLM inference in C/C++

Example projects using the AWS CDK

Production-ready platform for agentic workflow development.

CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model (CVPR 2024)

Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis

This is the code repo for ICCV23 paper Virtual Try-On with Garment-Pose Keypoints Guided Inpainting

Open-Sora: Democratizing Efficient Video Production for All

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

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

This project aim to reproducing Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.