↓ 8 callersFunctionscaled_dot_product_attention Apply scaled dot product attention. Args: qkv (torch.Tensor): A [N, L, 3, H, C] tensor containing Qs, Ks, and Vs.
iscene/trellis/modules/attention/full_attn.py:39
↓ 2 callersMethod__init__(self, factor: Union[int, Tuple[int, int, int], List[int]])
iscene/trellis/modules/sparse/spatial.py:64
↓ 2 callersFunctionsparse_scaled_dot_product_attention Apply scaled dot product attention to a sparse tensor. Args: qkv (SparseTensor): A [N, *, 3, H, C] sparse tensor containing Qs, Ks,
iscene/trellis/modules/sparse/attention/full_attn.py:20
↓ 1 callersMethod__init__(self, in_channels, out_channels, kernel_size, stride=1, dilation=1, bias=True, indice_key=None)
iscene/trellis/modules/sparse/conv/conv_torchsparse.py:7
↓ 1 callersMethod__init__(self, in_channels, out_channels, kernel_size, stride=1, dilation=1, padding=None, bias=True, indice_key=None)
iscene/trellis/modules/sparse/conv/conv_spconv.py:21