Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
badaoui 
posted an update 3 days ago
Post
226
Building high-performance, reproducible kernels for AMD ROCm just got a lot easier.

I've put together a guide on building, testing, and sharing ROCm-compatible kernels using the Hugging Face kernel-builder and kernels libraries; so you can focus on optimizing performance rather than spending time on setup.

Learn how to:

- Use Nix for reproducible builds
- Integrate kernels as native PyTorch operators
- Share your kernels on the Hub for anyone to use with kernels.get_kernel()

We use the 🏆 award-winning RadeonFlow GEMM kernel as a practical example.

📜 Check out the full guide here : https://huggingface.co/blog/build-rocm-kernels
In this post