Torch XPU Operators*

Torch XPU Operators* implements PyTorch ATen operators for Intel GPU devices, aiming to agilely support PyTorch ATen operations and buffer these operations for Intel GPU upstreaming . For more details, refer to SYCL kernels for ATen Operators RFC for more details.

Overview

• SYCL Implementation for XPU Operators: The Operators in this staging branch will finally be upstreamed to PyTorch for Intel GPU.

Requirements

For the hardware and software prerequiste, please refer to PyTorch Prerequisites for Intel GPUs to check your hardware and install the following packages.

• Intel GPU Driver: Install Intel GPU drivers along with compute and media runtimes and development packages.
• Intel® Deep Learning Essentials: Install a subset of Intel® oneAPI components needed for building and running PyTorch.

Build

Need to built this project as a submodule of PyTorch, after install Intel GPU Driver and Intel Deep Learning Essentials.

# Setup PyTorch source project. torch-xpu-ops is included by default.
python setup.py install

Security

See Intel's Security Center for information on how to report a potential security issue or vulnerability.

See also: Security Policy

License

Apache License 2.0