Released at the end of 2023 was [1]TurnkeyML as an open-source collaboration between ONNX and AMD developers . TurnkeyML has evolved into focusing on making it easy to use the most important tools within the ONNX ecosystem and their Lemonade SDK to deploy large language models on various devices/accelerators Out today is TurnkeyML 6.2 with a focus on delivering better AMD Ryzen AI NPU support.

With today's TurnkeyML 6.2 release the Ryzen AI NPU support is now available as a selectable device backend within the lemonade-install tool. Additionally, the Ryzen AI NPU and hybrid execution targets can be both installed into the same Python environment.

TurnkeyML 6.2 also now allows building optimized OGA checkpoints for the Ryzen AI NPU and hybrid targets.

Some of the other TurnkeyML 6.2 improvements include easy port selection for the Lemonade server and various new options.

Those wishing to learn more about the ONNX TurnkeyML 6.2 release can do so via [2]the project's GitHub .



[1] https://www.phoronix.com/news/ONNX-TurnkeyML

[2] https://github.com/onnx/turnkeyml/releases/tag/v6.2.0