afeldman-nmandWoosuk Kwon 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

..

backends

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

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

ops

[Bugfix] Add verbose error if scipy is missing for blocksparse attention (#5695)

2024-07-05 10:41:01 -07:00

__init__.py

[Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API (#4681)

2024-05-15 14:00:10 +09:00

layer.py

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

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

selector.py

[Kernel][Model] logits_soft_cap for Gemma2 with flashinfer (#6051)

2024-07-04 16:35:51 -07:00