We present Qiboml, an open-source software library for orchestrating quantum and classical components in hybrid machine learning workflows. Building on Qibo's quantum computing capabilities and integrating with popular machine learning frameworks such as TensorFlow and PyTorch, Qiboml enables the construction of quantum and hybrid models that can run on a broad range of backends: (i) multi-threaded CPUs, GPUs, and multi-GPU systems for simulation with statevector or tensor network methods; (ii) quantum processing units, both on-premise and through cloud providers. In this paper, we showcase its functionalities, including diverse simulation options, noise-aware simulations, and real-time error mitigation and calibration.
@article{arxiv.2510.11773,
title = {Qiboml: towards the orchestration of quantum-classical machine learning},
author = {Matteo Robbiati and Andrea Papaluca and Andrea Pasquale and Edoardo Pedicillo and Renato M. S. Farias and Alejandro Sopena and Mattia Robbiano and Ghaith Alramahi and Simone Bordoni and Alessandro Candido and Niccolò Laurora and Jogi Suda Neto and Yuanzheng Paul Tan and Michele Grossi and Stefano Carrazza},
journal= {arXiv preprint arXiv:2510.11773},
year = {2025}
}
Comments
14 pages, 13 figures. Package available at: https://github.com/qiboteam/qiboml