GitLab

Renamed the template parameter to a simpler name (it's the number of warps per tile used in the permutation).

* Replaced PyTorch's slow permutation.
* Split kernel into general and specialized versions (for num_channel <= 8192)
* Enabled float4-based vectorized memory access, when possible.
* Added runtime dispatch logic for kernel specialization.

Aligned attention_fwd_cuda.cu with attention_bwd_cuda.cu in terms of naming conventions and kernel parameters.

Extracted shared host/device functions and declarations into a separate module:
* attention_utils.cuh
* attention_utils.cu

* removing duplicate code from distributed convoloution

* replacing from_numpy with as_tensor

* make preprocess_psi_tensor GPU ready.