Comment by nl
4 months ago
I suspect the OP's issues might be mostly related to the ROCM version of PyTorch. AMD still can't get this right.
4 months ago
I suspect the OP's issues might be mostly related to the ROCM version of PyTorch. AMD still can't get this right.
Probably - but the answer is to avoid ROCM, not pytorch.
Avoiding ROCm means buying a new Nvidia GPU. Some people would like to keep using the hardware they already have.
The cost to deal with rocm is > cost of a consumer nvidia gpu by orders of magnitude.