does flash_mla_with_kvcache work only in paged mode? #126
Description
Is is possible to use it with kcache (and q, k) first dimension being the batch size ?
if not any plan to support the non paged mode ?
{{ message }}
Is is possible to use it with kcache (and q, k) first dimension being the batch size ?
if not any plan to support the non paged mode ?