pytorch/ao
PyTorch native quantization for training and inference
- Stars
- 3.0k
- Forks
- 656
- Open issues
- 306
- Last push
- today
About ao
ao is a free, open-source machine learning tool by pytorch, written mainly in Python. PyTorch native quantization for training and inference. It has 3.0k GitHub stars and 656 forks, and was last updated today. GitHub doesn't detect a standard license, so check the repository before using it commercially.
- License
- Not detected
- Language
- Python
- Stars
- 3,013
- Last update
- today
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not stated
- Self-hostable
- Not stated
Similar free tools
pytorch-image-models37k stars · The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT)
neural-compressor2.7k stars · SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
SwanLab4.3k stars · ⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / Ultr
LlamaFactory76k stars · Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
nncf1.2k stars · Neural Network Compression Framework for enhanced OpenVINO™ inference
uni2ts1.6k stars · Unified Training of Universal Time Series Forecasting Transformers
ao FAQ
Is ao free?
Yes. ao is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.
Does ao run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does ao need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is ao still maintained?
Yes. It was last updated today and has 306 open issues on GitHub.
What are alternatives to ao?
Similar free, open-source tools include pytorch-image-models, neural-compressor, SwanLab, LlamaFactory.