Component Name
Qiskit-Torch-Module
Maintainers
Fraunhofer IIS (Quantum Compilation Group)
Documentation URL
https://github.com/nicomeyer96/qiskit-torch-module/blob/main/README.md
PyPI Release URL
https://pypi.org/project/qiskit-torch-module/
GitHub Repository URL
https://github.com/nicomeyer96/qiskit-torch-module
Programming Languages
Python
Built on:
Qiskit
Description
The qiskit-torch-module is a Qiskit-based simulation and training framework for variational quantum circuits with a native PyTorch interface, designed for fast prototyping of quantum neural networks on single-CPU machines. It provides efficient multi‑observable evaluation, batch‑parallelized expectation and gradient computation, and flexible automatic differentiation for hybrid classical–quantum models. Compared to qiskit‑machine‑learning, it achieves up to two orders of magnitude lower runtimes with minimal code changes to existing Qiskit workflows.
Component Name
Qiskit-Torch-Module
Maintainers
Fraunhofer IIS (Quantum Compilation Group)
Documentation URL
https://github.com/nicomeyer96/qiskit-torch-module/blob/main/README.md
PyPI Release URL
https://pypi.org/project/qiskit-torch-module/
GitHub Repository URL
https://github.com/nicomeyer96/qiskit-torch-module
Programming Languages
Python
Built on:
Qiskit
Description
The qiskit-torch-module is a Qiskit-based simulation and training framework for variational quantum circuits with a native PyTorch interface, designed for fast prototyping of quantum neural networks on single-CPU machines. It provides efficient multi‑observable evaluation, batch‑parallelized expectation and gradient computation, and flexible automatic differentiation for hybrid classical–quantum models. Compared to qiskit‑machine‑learning, it achieves up to two orders of magnitude lower runtimes with minimal code changes to existing Qiskit workflows.