nndeploy
A visual workflow-based AI deployment framework for multi-platform and multi-backend inference, supporting large models and edge devices.
What is nndeploy?
nndeploy is an open-source AI deployment framework designed to simplify and accelerate the deployment of AI models across diverse platforms, including desktop, mobile, edge devices, and servers. It provides a visual workflow editor for drag-and-drop pipeline construction and supports multiple inference backends for high-performance execution.
AI engineers and developers who need to deploy and productionize AI models across heterogeneous environments, including desktop (Windows, macOS), mobile (Android, iOS), edge devices (NVIDIA Jetson, Ascend310B, RK), and servers (RTX series, T4, Ascend310P). It is also suitable for those deploying large models (10B+ parameters) like LLMs and AIGC generation models as a visual workflow tool.
Developers choose nndeploy for its combination of a visual, drag-and-drop workflow editor that simplifies pipeline construction with support for over 13 inference backends (like ONNXRuntime, TensorRT, OpenVINO) for flexible, high-performance execution across platforms. Its unique selling point is reducing the complexity of productionizing models by offering visual automation alongside deep performance optimizations like parallel execution and memory management.
Overview
一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework
Use Cases
Best For
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
