# for slice_size > 0 the attention score computation # is split across the batch axis to save memory # You can set slice_size with `set_attention_slice` self._slice_size = None self.to_q = nn.Linear(query_dim, inner_dim, bias=False) ...
master 216Branches 60Tags Code Folders and files Name Last commit message Last commit date Latest commit omahs Fix typos (#10119) Aug 21, 2024 d91b734·Aug 21, 2024 History 2,761 Commits .github update build files cuda versions (#10117) ...