- torch.mm(input, mat2, *, out=None) Tensor ¶
Performs a matrix multiplication of the matrices
inputis a tensor,
mat2is a tensor,
outwill be a tensor.
This function does not broadcast. For broadcasting matrix products, see
Supports strided and sparse 2-D tensors as inputs, autograd with respect to strided inputs.
This operation has support for arguments with sparse layouts. If
outis provided it’s layout will be used. Otherwise, the result layout will be deduced from that of
Sparse support is a beta feature and some layout(s)/dtype/device combinations may not be supported, or may not have autograd support. If you notice missing functionality please open a feature request.
This operator supports TensorFloat32.
On certain ROCm devices, when using float16 inputs this module will use different precision for backward.
- Keyword Arguments:
out (Tensor, optional) – the output tensor.
>>> mat1 = torch.randn(2, 3) >>> mat2 = torch.randn(3, 3) >>> torch.mm(mat1, mat2) tensor([[ 0.4851, 0.5037, -0.3633], [-0.0760, -3.6705, 2.4784]])