A Python program that generates a hardware-accelerated inference runtime from an ONNX model. Both the hardware and the software that drives it are generated automatically, meaning that we are essentially making a Model -> Runtime compiler. The runtime is intended to run in an embedded system and be accelerated by a custom accelerator generated by Versat, a CGRA compiler.
An AI generated wiki for versat-ai is available here
Currently the project is capable of running a decent amount of CNNs. Not all Onnx operators are supported but we support the most common ones. Some graph optimizations exist but optimization logic is still not finished and not guaranteed to actually perform better than a non optimized graph. Requires fine tuning.
To run a simple test, simply run the command '''make pc-emul-run'''. This test is generated by creating a onnx model with each currently supported operator, creating random tests for each operator and then generating the runtime and running it in the emulation environment provided by the py2hwsw project.
To run the same test in simulation, run the command '''make sim-run'''.
This project was funded through the NGI0 Core Fund, a fund established by NLnet with financial support from the European Commission's Next Generation Internet programme, under the aegis of DG Communications Networks, Content and Technology under grant agreement No 101092990.
The work has been partially performed in the scope of the A-IQ Ready project, which receives funding within Chips Joint Undertaking (Chips JU) - the Public-Private Partnership for research, development, and innovation under Horizon Europe – and National Authorities under grant agreement No. 101096658.
The A-IQ Ready project is supported by the Chips Joint Undertaking (Chips JU) - the Public-Private Partnership for research, development, and innovation under Horizon Europe – and National Authorities under Grant Agreement No. 101096658.
![]() |
![]() |

