afeldman-nm 543aa48573 [Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support) (#4888) ...

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2024-07-08 17:12:15 +00:00

36 KiB

Raw Blame History

View Raw