vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl ¶

logger `module-attribute` ¶

logger = init_logger(__name__)

decode(
    z: Tensor,
    return_dict: bool = True,
    *args: Any,
    **kwargs: Any,
)

from_config(*args: Any, **kwargs: Any)

from_pretrained(*args: Any, **kwargs: Any)

patch_exec(task: TileTask) -> Tensor

patch_merge(
    coord_tensor_map: dict[tuple[int, ...], Tensor],
    grid_spec: GridSpec,
) -> Tensor

patch_split(z: Tensor) -> tuple[list[TileTask], GridSpec]

tile_exec(task: TileTask) -> Tensor

Decode a single latent tile into RGB space.

tile_merge(
    coord_tensor_map: dict[tuple[int, ...], Tensor],
    grid_spec: GridSpec,
) -> Tensor

Merge decoded tiles into a full image.

tile_split(z: Tensor) -> tuple[list[TileTask], GridSpec]