Retrieval-based-Voice-Conversion-WebUI icon indicating copy to clipboard operation
Retrieval-based-Voice-Conversion-WebUI copied to clipboard

PLEASE ADD DirectML support

Open 6p5ra opened this issue 2 years ago • 1 comments

Greetings from the doomed AMD users who don't have CUDA. :)

6p5ra avatar Jun 22 '23 02:06 6p5ra

I tried injecting self.device = torch_directml.device() but it seems fairseq uses legacy construction and PyTorch is not happy with it.

Related: microsoft/DirectML#400 pytorch/pytorch#95748. The latter is already merged but it seems not in PyTorch 2.0.1 yet.

MikuAuahDark avatar Jun 29 '23 13:06 MikuAuahDark

This issue was closed because it has been inactive for 15 days since being marked as stale.

github-actions[bot] avatar Apr 29 '24 04:04 github-actions[bot]