Why x-attention only support batch size = 1 when it used block-sparse-attention repo?

[ZetangForward]

I notice x-attention only supports batch size = 1 when it applies block sparse attention:

https://github.com/mit-han-lab/x-attention/blob/b4794c3a976fb9640af2730b95c42df485e9880e/xattn/src/Xattention.py#L355

Can x-attention support a larger batch size when using the block-sparse attention repo? (more than 1)

[wtarp]

Same question here