search

BlackSamorez / tensor_parallel

Automatically split your PyTorch models on multiple GPUs for training & inference
MIT License
629 stars 39 forks source link

hotfix canonic torch.device #37

Closed justheuristic closed 1 year ago

justheuristic commented 1 year ago

The edited line would previously fail because torch.device(type=...index=0) requires type to be str, not device