Qwen, ModelScope, DashScope, and Alibaba Cloud AI
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
JavaScript in-page GUI agent. Control web interfaces with natural language.
Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.
Alibaba Cloud's high-performance KVCache system for LLM inference, with components for global cache management, inference simulation(HiSim), and more.
A construction kit for reinforcement learning environment management.
Agentic AI Framework for Java Developers
AgentEvolver: Towards Efficient Self-Evolving Agent System
An open-source AI agent that lives in your terminal.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...) (AAAI 2025).
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Secure, Fast, and Extensible Sandbox runtime for AI agents.
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
The UI design language and React library for Conversational UI
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
A series of math-specific large language models of our Qwen2 series.
Enjoy the magic of Diffusion models!
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
ModelScope: bring the notion of Model-as-a-Service to life.
A lightweight, lightning-fast, in-process vector database
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.
MS-Agent: a lightweight framework to empower agentic execution of complex tasks
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab
[CVPR2024 (Highlight)] RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. Live Demo：https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
[CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation
An all-in-one toolkit for computer vision
StarCraft environment for OpenAI Gym, based on Facebook's TorchCraft. (In progress)
SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
An Industrial Graph Neural Network Framework
An industrial deep learning framework for high-dimension sparse data
Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
A distributed graph deep learning framework.
Machine learning platform for Web developers
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
Alink is the Machine Learning algorithm platform based on Flink, developed by the PAI team of Alibaba computing platform.
BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
Generative Pre-trained Graph Eulerian Transformer [ICML2025]
EasyRobust: an Easy-to-use library for state-of-the-art Robust Computer Vision Research with PyTorch.