Distributed query engine providing simple and reliable data processing for any modality and scale

Automated deployment of large-scale sharding services on kubernetes.

Automated deployment of large-scale sharding services on kubernetes.

Build domain AI assistants with annotated dialogue examples - 通过标注对话示例，低成本构建可靠智能体

Delivers efficient, stable, and secure data distribution and acceleration powered by P2P technology, with an optional content‑addressable filesystem that accelerates OCI container launch.

A modern replacement for Redis and Memcached

A flexible serving framework that delivers efficient and fault-tolerant LLM inference for clustered deployments.

A high-performance inference engine for LLMs, optimized for diverse AI accelerators.

DLRover: An Automatic Distributed Deep Learning System

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

TradingAgents: Multi-Agents LLM Financial Trading Framework

Scalable and user friendly neural 🧠 forecasting algorithms.

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730

Fast, Flexible and Portable Structured Generation

Python爬虫练习案例，循序渐进从入门到进阶

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…

A modular graph-based Retrieval-Augmented Generation (RAG) system

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

DeepRec Extension is an easy-to-use, stable and efficient large-scale distributed training system based on DeepRec.

An industrial deep learning framework for high-dimension sparse data

A generative speech model for daily dialogue.

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

LLM training in simple, raw C/CUDA

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

The Modular Platform (includes MAX & Mojo)