torch.nn.functional.linear — PyTorch 2.7 documentation (original) (raw)

torch.nn.functional.linear(input, weight, bias=None) → Tensor¶

Applies a linear transformation to the incoming data: y=xAT+by = xA^T + b.

This operation supports 2-D weight with sparse layout

Warning

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.

Shape:

• Input: (∗,in_features)(*, in\_features) where * means any number of additional dimensions, including none
• Weight: (out_features,in_features)(out\_features, in\_features) or (in_features)(in\_features)
• Bias: (out_features)(out\_features) or ()()
• Output: (∗,out_features)(*, out\_features) or (∗)(*), based on the shape of the weight