Enjoy the magic of Diffusion models!

Wan: Open and Advanced Large-Scale Video Generative Models

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"

Kronos: A Foundation Model for the Language of Financial Markets

Unified Training of Universal Time Series Forecasting Transformers

Chronos: Pretrained Models for Time Series Forecasting

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

Implementations, Pre-training Code and Datasets of Large Time-Series Models

Official reinforcement learning environment for demand response and load shaping

Official repo for CFG-Zero*

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

A framework for few-shot evaluation of language models.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Serverless Workflow Management System (WFMS)

"VideoRAG: Chat with Your Videos"

"MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Fully open reproduction of DeepSeek-R1

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

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

前端低代码框架，通过 JSON 配置就能生成各种页面。

The easiest & fastest way to run customized and fine-tuned LLMs locally or on the edge

The official Rust implementation of Conflux protocol. https://doc.confluxnetwork.org