Steps to reproduce
import torch
def func(x1, x2):
return torch.bitwise_and(x1, x2)
x1 = torch.tensor([True, True, False], device="cuda")
x2 = torch.tensor([False, True, False], device="cuda")
func(x1, x2) # --> runs
torch.compile(func, backend="tvm")(x1, x2) # --> not implemented error
Triage
Please refer to the list of label tags here to find the relevant tags and add them below in a bullet format (example below).