xma.functional.swiglu_packed¶
- swiglu_packed(x: Tensor, *, kernel_backend: KernelBackend | None = None) Tensor[source]¶
computes swiglu activation by splitting the tensor x into 2 parts: gate and up activations
- Parameters:
x (torch.Tensor) – input activation
kernel_backend (KernelBackend | None) – KernelBackend
- Returns:
output tensor
- Return type:
Tensor