MegEngine/MegFlow
MegEngine/MegFlow has 400 GitHub stars and 37 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-09 12:48 UTC. Last push 2023-05-26.
Efficient ML solution for long-tailed demands.
What you can do
- Efficient runtime schedule based on async-std[features=tokio1]
- Use toml to construct pipeline
- Support static/dynamic/share subgraph
- Support Rust and Python
Measured star growth
- in 24h
- 0
- in 7 days
- Collecting history
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
README.md
Original
简体中文 | English
MegFlow | Documentation
Build video analysis service in 15 minutes.
- Directly use Python to build pipeline
- No need C++ SDK anymore, improve the development experience
- Provide one-stop service for construction, testing, debugging, deployment, and visualization
HowTo
- how to run
- how to build
- how to use
- how to debug
- how to contribute
- FAQ
Current Support Matrix
| Platform | win10 docker/wsl2 | ubuntu | centOS | macos |
|---|---|---|---|---|
| x86 | ✔️ | ✔️ | ✔️ | ✔️ |
| ARMv8 | - | ✔️ | ✔️ | - |
| Python verion | support |
|---|---|
| 3.6 | ✔️ |
| 3.7 | ✔️ |
| 3.8 | ✔️ |
| 3.9 | ✔️ |
Built-in Applications
Features
- Efficient runtime schedule based on async-std[features=tokio1]
- Use toml to construct pipeline
- Support static/dynamic/share subgraph
- Support Rust and Python
- Support resource management
- Terminate static subgraph in exception processing
- Support demux/reorder/transform
- Use Python stackfull coroutine
- Support plugin sandbox
- Real-time preview constructing pipeline
Coming Soon
- Process-level node
- Plug-in automated test
- Performance monitoring
- More built-in applications
Contact Us
- Issue: github.com/MegEngine/MegFlow/issues
- Email: [email protected]
- QQ Group: 1029741705
License
Explore related projects
tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
201,400 starshuggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
168,668 starsAUTOMATIC1111/stable-diffusion-webui
Stable Diffusion web UI
165,261 starsComfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
145,835 stars