GATConv edge_attr throws error

[Sanjaykrishnamurthy]

import torch
from torch_geometric.data import Data

edge_index = torch.tensor([[0, 1, 1, 2],
                           [1, 0, 2, 1]], dtype=torch.long)
x = torch.tensor([[2], [0], [1]], dtype=torch.long)
edge_attr = torch.tensor([[1,1,0,0],[1,1,0,0],[0,1,0,0],[1,1,0,0]], dtype=torch.long)
data = Data(x=x, edge_index=edge_index, edge_attr=edge_attr)

embedding = nn.Embedding(10, 3)
x_emb = embedding(data.x.long())
x_emb = x_emb.squeeze()

gat = GATConv(3, 3, edge_dim=4)
output= gat(x=x_emb, edge_index=data.edge_index.type(torch.LongTensor), edge_attr=edge_attr.type(torch.LongTensor))

Throws the error
RuntimeError: expected scalar type Long but found Float

torch version is 1.13.1
pyg version is 2.2.0

Thanks for the help

[Sanjaykrishnamurthy]

with torch - 2.0.0+cu117 and pyg - 2.3.0, this works perfect