in-place copy from src to dst src and dst should be the same layer type, e.g., both are LayerNorm or both are Linear. Or at least, bo

in-place copy from src to dst src and dst should be the same layer type, e.g., both are LayerNorm or both are Linear. Or at least, bo

in-place copy from src to dst src and dst should be the same layer type, e.g., both are LayerNorm or both are Linear. Or at least, bo

in-place copy from src to dst src and dst should be the same layer type, e.g., both are LayerNorm or both are Linear. Or at least, bo

Decode a batch of images/videos. Args: z (`torch.FloatTensor`): Input batch of latent vectors. return_d

videos: A list of videos each with shape [C, T, H, W].

Precompute the frequency tensor for complex exponentials (cis) with given dimensions. This function calculates a frequency tensor with compl

r""" Compute the attention scores. Args: query (`torch.Tensor`): The query tensor. key (`torch.Tensor`): The

Get the data parallel group the caller rank belongs to.

Get the data parallel group the caller rank belongs to.

Build the model.

Returns: all_datasets: Dict[str, List[Dataset]], mapping from split to list of datasets collator_fn: Callable

Preprocess a batch of images. Args: images (`ImageInput`): A list of images to preprocess. d

Init method based on N(0, sigma).