CUDA for AMD on Windows
A new technical project enables the execution of CUDA-based Windows applications on AMD GPUs using ZLUDA and the ROCm/HIP stack. The project provides a reproducible setup for compute-heavy workloads, though compatibility is currently limited to specific hardware.
Why it matters
This project challenges the NVIDIA-dominated AI hardware ecosystem by providing a path for AMD users to run CUDA-dependent software.
WORKING REPRODUCIBLE STACK IS NOW UPLOADED.
Run CUDA-targeted Windows applications on AMD GPUs through ZLUDA + ROCm/HIP.
A reproducible Windows CUDA compatibility setup built around ZLUDA + AMD HIP/ROCm . It is intended for CUDA-facing compute applications, including workloads that use CUDA-enabled LibTorch.
Validated hardware is currently AMD Radeon RX 9060 XT ( gfx1200 ) only. Other AMD GPUs are candidates, not guaranteed working devices. If you test another card, please open a GPU compatibility report , whether it works or fails.
The public, upstream-only path has been tested without any private/recovered DLLs:
That integration test used the same CUDA-facing LibTorch training workload that originally motivated this project. See docs/VALIDATION.md .
This does not mean every CUDA program or AI model works. CUDA API/library coverage is workload-dependent.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in