New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

How to implement a C++ custom op with cuda support? #181

Open

luchangli03 opened this issue Nov 1, 2021 · 1 comment

luchangli03 commented Nov 1, 2021

How to implement a C++ custom op with cuda support?
Moreover, I didn't even find a detailed example about how to write a c++ costom op in C++, there is just an outdated tutorial: https://github.com/microsoft/onnxruntime-extensions/blob/main/tutorials/cpp_custom_ops_tutorial.md.

Member

wenbingl commented Nov 2, 2021 •

edited

Loading

There is no cuda kernel for custom op in this project.
But ONNXRuntime does support CUDA for a custom op, you can check here for more detail: https://onnxruntime.ai/docs/reference/operators/add-custom-op.html#cuda-custom-ops

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment