Steps to reproduce
from tvm import relay
import torch
def func(x):
return torch.linalg.vector_norm(x)
x = torch.rand(3, 3)
scripted_func = torch.jit.trace(func, x)
print(scripted_func(x))
input_infos = [('x', (x.shape, 'float32'))]
mod, params = relay.frontend.from_pytorch(scripted_func, input_infos)
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).
cc @shingjan @yelite