Today myself, Andreas Fehlner, and Adam Pocock made a presentation to the ONNX steering committee to propose new working groups around ONNX support for Bayesian Models from various frameworks. The working groups are not approved yet but we would like to gauge community feedback from this type of work and also do people want more ONNX support for Bayesian Models and Inference from frameworks like Stan, PyMC, Pyro, Numpyro, Tensorflow Probability, and many others. Please drop a comment if you like around what you want from ONNX in terms of support for these frameworks and how can ONNX be more useful in deployment of these models.
Nice initiative. From memory onnx is missing some basic linalg ops like solves, cholesky that show up all the time with multivariate distributions plus special math funcions
Understood, we would also make the necessary operators and distributions that would be necessary in order for you to have those representations in ONNX that’s part of the plan.