Where is the nn.Linear cuda implementation

I cannot find the cuda implementation of nn.Linear, for forward implementation and backward implementation. Can anyone helps me with this?

nn.Linear is using F.linear, which will call into addmm or matmul here and then deploy to the cublas method here.

Thanks for the answer. And btw, what is the backward function/implementation for the F.linear? I see many Ops defined their related backward functions in native_functions.yaml file, but for thoes not defined , how do we check their backward implmenetation? Is there a common way?

The backward methods of the aforementioned functions are defined in the derivatives.yaml as seen here.