Speedstu · 2026-09-13 · notable
CUDA for AMD on Windows — ZLUDA and ROCm wired up by one script
CUDA-for-AMD-Windows runs unmodified CUDA Windows programs on AMD GPUs by putting ZLUDA in front of AMD's HIP/ROCm stack. A PowerShell installer assembles the runtime; the author validated it on a Radeon RX 9060 XT.
A scripted Windows setup that lets CUDA-built apps run on an AMD Radeon card through ZLUDA and the HIP SDK.
What is it?
CUDA-for-AMD-Windows packages the ZLUDA-on-ROCm route into an installer you can actually follow. ZLUDA catches the CUDA calls an application makes and sends them to AMD's HIP/ROCm runtime instead, so the CUDA binary runs unchanged and never learns it is on an AMD GPU. The repo pins ZLUDA v6-preview.69 and targets the Windows HIP SDK 6.4.
How does it work?
install.ps1 builds the runtime from three pieces: the AMD GPU driver and Windows HIP SDK, an official ZLUDA release, and an optional LibTorch 2.3.0+cu118. stage-runtime.ps1 then drops the compatibility libraries next to the executable, and run-zluda.ps1 starts the program through zluda.exe with the HIP libraries on PATH. Helper scripts cover the rest — gpu-scan.ps1 detects the AMD architecture through hipInfo.exe, doctor.ps1 checks the libraries are present, and test-runtime.ps1 runs the compatibility suite.
Why does it matter?
Windows has been the weak spot for AMD compute: ROCm's Linux story is far ahead, so CUDA-only tools tend to mean buying an Nvidia card. This repo gives a concrete, reproducible path with the limits written down rather than promised away. The CUDA driver API, cuBLAS, cuBLASLt, cuSPARSE and cuFFT resolve; cuDNN/MIOpen, NCCL, TensorRT and custom CUDA extensions do not, so coverage is per workload, not blanket compatibility.
Who is it for?
AMD GPU owners running CUDA-only Windows tools
Try it
powershell -ExecutionPolicy Bypass -File .\scripts\install.ps1