🐛 Describe the bug

Running the following PyTorch code results in a Floating point exception crash:

import torch

x = torch.randn(2, 64, 32, 32).to_mkldnn()
out2 = torch.mkldnn_max_pool2d(x, kernel_size=3, stride=0)

Versions

PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

cc @malfet @gujinghui @PenghuiCheng @XiaobingSuper @jianyuh @jgong5 @mingfeima @sanchitintel @ashokei @jingxu10 @min-jean-cho @yanbing-j @Guobing-Chen @Xia-Weiwen @snadampal