AMD显卡免换卡跑CUDA程序
推荐指数 75.0 NO. 011 · 2026.09.14
发布2026/09/13Score102Comments58
为什么值得看
ZLUDA+ROCm方案首次在Windows上实现可复现的CUDA兼容，RX 9060 XT已验证可跑LibTorch等计算负载。对持有AMD显卡的AI开发者意味着无需双卡或换卡即可运行CUDA生态工具。
编辑判断
之前AMD跑CUDA的解决方案要么依赖Linux（如HIPify），要么需要私泄的nvcuda.dll，法律风险高且不可持续。这个项目的价值在于走通了纯上游开源组件的Windows路径，彻底摆脱了对NVIDIA私有驱动的依赖。
但限制也很明显：目前仅验证RX 9060 XT一款显卡，且ZLUDA本身对CUDA runtime的覆盖率并非100%，复杂算子（如NCCL、TensorRT）大概率仍跑不通。如果你手边正好是这张卡且主要用LibTorch做推理，可以立即试水；如果是生产环境或依赖完整CUDA工具链，建议继续观望兼容性报告积累情况。
短期对NVIDIA生态构不成实质威胁，但会降低个人开发者和小团队的CUDA锁定效应，特别是显卡预算敏感的中国市场。
社区反馈
意见分歧 37 条评论
核心争论：CUDA兼容方案实用性与开源标准路线之争
CUDA for AMD on Windows I’ve been working on a Windows setup that lets CUDA-targeted applications run on AMD GPUs using ZLUDA + ROCm/HIP. Repo: https://github.com/Speedstu/CUDA-for-AMD-Windows So far, it has only been tested on my RX 9060 XT (gfx1200), where I’ve used it wit
(As a side note, I love the name ZLUDA; it very aptly means "delusion" or "deception" in Polish.)
TIL, I didn’t know that. I always assumed it came from level zero”, the Intel computer layer that ZLUDA was translating to before its developer was hired by AMD to target HIP.