Welcome to ONNX TurnkeyML

We are on a mission to make it easy to use the most important tools in the ONNX ecosystem. TurnkeyML accomplishes this by providing no-code CLIs and low-code APIs for both general ONNX workflows with turnkey as well as LLMs with lemonade.

Lemonade	Turnkey
Serve and benchmark LLMs on CPU, GPU, and NPU. Click here to get started with lemonade.	Export and optimize ONNX models for CNNs and Transformers. Click here to get started with turnkey.

How It Works

The turnkey (CNNs and transformers) and lemonade (LLMs) CLIs provide a set of Tools that users can invoke in a Sequence. The first Tool takes the input (-i), performs some action, and passes its state to the next Tool in the Sequence.

You can read the Sequence out like a sentence. For example, the demo command above was:

> turnkey -i bert.py discover export-pytorch optimize-ort convert-fp16

Which you can read like:

Use turnkey on bert.py to discover the model, export the pytorch to ONNX, optimize the ONNX with ort, and convert the ONNX to fp16.

You can configure each Tool by passing it arguments. For example, export-pytorch --opset 18 would set the opset of the resulting ONNX model to 18.

A full command with an argument looks like:

> turnkey -i bert.py discover export-pytorch --opset 18 optimize-ort convert-fp16

Contributing

We are actively seeking collaborators from across the industry. If you would like to contribute to this project, please check out our contribution guide.

Maintainers

This project is sponsored by the ONNX Model Zoo special interest group (SIG). It is maintained by @danielholanda @jeremyfowers @ramkrishna @vgodsoe in equal measure. You can reach us by filing an issue or emailing turnkeyml at amd dot com.

License

This project is licensed under the Apache 2.0 License.

Attribution

TurnkeyML used code from other open source projects as a starting point (see NOTICE.md). Thank you Philip Colangelo, Derek Elkins, Jeremy Fowers, Dan Gard, Victoria Godsoe, Mark Heaps, Daniel Holanda, Brian Kurtz, Mariah Larwood, Philip Lassen, Andrew Ling, Adrian Macias, Gary Malik, Sarah Massengill, Ashwin Murthy, Hatice Ozen, Tim Sears, Sean Settle, Krishna Sivakumar, Aviv Weinstein, Xueli Xao, Bill Xing, and Lev Zlotnik for your contributions to that work.