[CPU] Fix wrong offset for non-contiguous conv2d im2col kernels (#3736)

conv2d_im2col_gemm copies a non-contiguous kernel into a fresh contiguous
buffer that starts at index 0, but it built the matmul layout using the
original strided kernel's start offset. For a kernel with a non-zero start
offset, such as a channel slice of a larger pointwise weight, the matmul
read past the materialized buffer and produced incorrect forward values and
gradients. Use offset 0 so the layout matches the materialized buffer.

Co-authored-by: ivarflakstad <69173633+ivarflakstad@users.noreply.github.com>