def _get_unpad_data()

in deepseek_vl2/models/modeling_deepseek.py [0:0]

• 12 lines of code
• 1 McCabe index (conditional complexity)

def _get_unpad_data(attention_mask):
    seqlens_in_batch = attention_mask.sum(dim=-1, dtype=torch.int32)
    indices = torch.nonzero(attention_mask.flatten(), as_tuple=False).flatten()
    max_seqlen_in_batch = seqlens_in_batch.max().item()
    cu_seqlens = F.pad(
        torch.cumsum(seqlens_in_batch, dim=0, dtype=torch.torch.int32), (1, 0)
    )
    return (
        indices,
        cu_seqlens,
        max_seqlen_in_batch,
    )