-
-
Notifications
You must be signed in to change notification settings - Fork 514
DirectML
SD.Next includes support for PyTorch-DirectML.
Important
DirectML support is marked as End-of-Life (EOL) and will be removed in the future releases
torch-directml received no updates in over 1 year and its currently superceded by rocm or zluda
Add --use-directml on commandline arguments.
For details, go to Installation.
The performance is quite bad compared to ZLUDA and ROCm.
If your card is relatively new and you prefer Windows system, we recommend ZLUDA.
If you are familiar with Linux system, we recommend ROCm.
PyTorch-DirectML does not access graphics memory by indexing. Because PyTorch-DirectML's tensor implementation extends OpaqueTensorImpl, we cannot access the actual storage of a tensor.
If you met RuntimeError with no error message (or empty), please report us via GitHub issue or Discord. (please check whether there's a duplicated issue)
If it works with FP32, please report us via GitHub issue or Discord. (please check whether there's a duplicated issue)
Please report us via GitHub issue or Discord. (please check whether there's a duplicated issue)
Refer to ONNX Runtime