Add heuristic default block sizes for different cases in ragged attention kernel #8922
Add heuristic default block sizes for different cases in ragged atten…
64ac8b68
fix
437fa7d9
fix
e4a23760
fix
3e54ecbe
fix
faa2d2a1
fix block size
56147e0f
set v4 of vmem_limit_bytes to 16MB
8286d566
yaochengji
force pushed
from
64d9bad4
to
8286d566
1 year ago
fix
119a50b6
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub