Updated: Nov 20, 2019
The Linux Foundation today announced that ONNX, the open format that makes machine learning models more portable, is now a graduate-level project inside of the organization’s AI Foundation. ONNX was originally developed and open-sourced by Microsoft and Facebook in 2017 and has since become somewhat of a standard, with companies ranging from AWS to AMD, ARM, Baudi, HPE, IBM, Nvidia and Qualcomm supporting it. In total, more than 30 companies now contribute to the ONNX code base.
It’s worth noting that only the ONNX format is included here, not the ONNX runtime, which Microsoft open-sourced a year ago. The runtime is an inference engine for models in the ONNX format and I wouldn’t be surprised if, at some point, Microsoft put that under the guidance of a foundation, too… but for now, that’s not the case.
“ONNX is not just a spec that companies endorse, it’s already being actively implemented in their products,” said Dr. Ibrahim Haddad, executive director of the LF AI Foundation, in today’s announcement. “This is because ONNX is an open format and is committed to developing and supporting a wide choice of frameworks and platforms. Joining the LF AI shows a determination to continue on this path, and will help accelerate technical development and connections with the wider open source AI community around the world.”
In its own announcement, Microsoft stressed that it remains committed to ONNX and highlights the work it did on making it easier to generate ONNX models from popular frameworks like PyTorch, TensorFlow, Keras and SciKit-Learn. “We are proud of the progress that ONNX has made and want to recognize the entire ONNX community for their contributions, ideas, and overall enthusiasm,” wrote Eric Boyd, the corporate VP at Microsoft in charge of Azure AI (not Microsoft AI). “We are excited about the future of ONNX and all that is to come.”